Traces

Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.

Astronomy Toolkit

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9999$74.48265.3M811k19h 2m65324
2Gemini 4 Argon0.9999$11.6230.2M300k2h 33m1313
3Claude Opus 5.50.9931$69.52233.4M859k17h 56m58725
4Claude Opus 5.50.9907$77.01274.8M827k18h 8m66937
5Claude Fable 50.9249$134.09102.7M413k9h 12m28920
6Claude Opus 50.9214$95.87150.8M548k9h 35m3375
7Claude Opus 50.9179$89.22139.0M522k13h 10m3206
8Claude Sonnet 5.50.9039$64.46256.3M1.0M13h 39m59911
9Claude Sonnet 5.50.9012$70.07279.4M1.1M11h 52m61811
10Gemini 4 Argon0.8999$8.3227.3M281k1h 26m1172
11Claude Fable 50.8978$116.4485.6M417k5h 53m27112
12Claude Fable 5.10.8953$64.06109.1M391k4h 49m30517
13Claude Fable 5.10.8935$57.2297.5M350k6h 25m29824
14Claude Opus 50.8866$79.79122.4M498k14h 37m3034
15Claude Fable 50.8818$104.8977.6M364k13h 47m2619
16Claude Opus 5.50.8205$49.70176.5M532k9h 15m36210
17GPT-6 Astra0.8045$135.6567.7M278k2h 40m2775
18Claude Fable 5.10.8000$36.7659.7M285k3h 53m22011
19Claude Fable 5.10.7999$32.0151.0M267k3h 57m20212
20Claude Fable 50.7998$113.8982.7M426k7h 1m2609
21GPT-6 Astra0.7969$2365.471121.6M2.3M19h 43m254849
22Claude Fable 5.10.7955$42.1068.8M317k4h 11m23212
23Claude Opus 50.7648$96.45153.7M524k15h 7m3585
24Claude Fable 50.7616$120.5789.4M424k12h 14m28010
25Gemini 3.7 Flash0.7294$8.3949.1M408k2h 12m2181
26GPT-6 Astra0.7058$233.15111.6M353k2h 41m35610
27Gemini 3.8 Flash0.7044$5.0541.3M227k1h 51m2182
28Claude Opus 5.50.7024$55.16202.1M545k11h 37m41316
29GPT-6 Astra0.7013$86.8245.8M224k2h 2m2145
30GLM-5.30.6985$72.52246.9M707k19h 16m5996
31GPT-6 Astra0.6917$365.75173.3M402k3h 17m4577
32Claude Sonnet 5.50.6877$35.84138.7M621k5h 52m2695
33Claude Opus 50.6837$80.75120.3M550k6h 30m2727
34Kimi K30.6250$60.98152.4M478k16h 31m41412
35Claude Sonnet 5.50.5306$67.58269.9M1.1M17h 27m6309
36Grok 4.60.5299$15.5715.6M323k1h 52m1064
37Gemini 4 Argon0.5135$11.8339.0M318k1h 48m1542
38GPT-5.6 Sol0.4849$43.3852.6M186k3h 16m2635
39Claude Haiku 5.50.4030$8.08127.7M586k6h 4m2752
40Claude Sonnet 5.50.4029$56.04216.5M989k10h 27m5468
41GLM-5.30.4028$57.26195.8M552k12h 7m4268
42Qwen3.8-Max-09020.4022$62.34193.6M1.6M19h 35m6633
43GLM-5.30.4017$72.89226.5M514k17h 29m4766
44Gemini 3.7 Flash0.4014$3.0923.0M225k38m1533
45Grok 4.60.3993$48.1146.2M395k3h 31m2086
46Kimi K30.3983$90.41238.0M505k20h 1m58720
47Kimi K30.3959$20.0846.3M279k6h 2m2055
48GLM-5.30.3930$77.97220.3M559k15h 22m4812
49Kimi K30.3804$70.49167.8M452k19h 35m4688
50Claude Haiku 5.50.3093$8.98142.5M643k5h 2m2904
51Grok 4.70.3076$28.4528.6M218k1h 15m1425
52Claude Haiku 5.50.3019$6.55100.4M539k4h 3m2481
53Gemini 3.8 Flash0.2999$4.7840.8M198k1h 11m2254
54Grok 4.70.2999$23.3123.1M224k1h 29m1183
55Kimi K30.2995$53.30137.6M418k11h 54m4307
56GLM-5.3 Flash0.2975$5.82179.7M476k11h 27m4534
57Qwen3.8-Max-09020.2897$62.30208.2M1.4M20h 2m5061
58GLM-5.30.2893$64.65196.5M549k19h 1m4198
59Muse Spark 1.30.2056$84.96112.8M364k5h 13m42819
60Grok 4.60.2000$34.6834.5M354k2h 42m1758
61Grok 4.60.1971$39.6635.3M400k3h 43m16511
62GPT-5.6 Sol0.1823$39.2848.9M195k2h 7m2554
63GLM-5.3 Flash0.1158$3.0893.0M371k3h 57m3203
64Claude Haiku 5.50.1077$9.75147.2M915k6h 7m3807
65Gemini 3.8 Flash0.1037$5.8854.2M233k1h 9m2553
66Muse Spark 1.30.1015$57.0570.7M278k5h 16m36111
67Muse Spark 1.20.1013$11.0759.7M393k2h 7m2591
68Muse Spark 1.20.1000$12.1666.0M402k2h 34m2314
69Muse Spark 1.30.0976$81.1381.9M258k12h 38m3972
70Muse Spark 1.20.0563$26.3390.8M427k5h 8m2972
71Claude Haiku 5.50.0349$11.89182.6M1.1M7h 13m4583
72Muse Spark 1.30.0279$94.7498.7M274k19h 49m42638
73Grok 4.70.0108$18.1818.2M206k1h 1m1053
74Grok 4.70.0075$224.04218.5M550k3h 42m69915
75Qwen3.8-Max-09020.0063$53.54172.9M1.4M19h 54m4081
76Grok 4.70.0032$13.3314.3M178k52m902
77Muse Spark 1.30.0028$18.8927.3M239k2h 57m1754
78Qwen3.8-Max-09020.0016$62.25179.2M2.0M19h 45m5132
79GLM-5.3 Flash0.0006$4.33118.3M395k10h 5m3883
80Qwen3.8-Max-09020.0003$33.8290.4M1.2M20h 0m3091
81Qwen3.8-Max0.0000$42.82145.6M925k17h 28m5242
82GLM-5.3 Flash0.0000$10.24291.8M558k13h 32m6312
83Inkling0.0000$4.594.7M24k22m1052
84DeepSeek V4 Flash Vision Exp0.0000$4.02226.3M587k18h 16m5035
85Inkling0.0000$5.986.1M33k29m1441
86DeepSeek V4 Flash Vision Exp0.0000$4.14229.6M637k20h 0m4831
87GPT-5.6 Sol0.0000$29.7437.3M170k2h 5m2118
88Gemini 3.8 Flash0.0000$5.1943.5M254k50m2313
89Qwen3.8-Max0.0000$48.24157.1M1.3M19h 42m5182
90Gemini 4 Argon0.0000$8.8535.0M322k1h 26m1372
91Gemini 3.7 Flash0.0000$5.4438.0M299k1h 47m1973
92Inkling0.0000$2.972.9M45k43m1092
93Muse Spark 1.20.0000$53.10223.4M907k9h 16m5353
94DeepSeek V4 Flash Vision Exp0.0000$3.11165.3M552k9h 15m4096
95GLM-5.3 Flash0.0000$6.17161.9M462k9h 59m4523
96Muse Spark 1.20.0000$11.0558.0M328k3h 11m2412
97Gemini 4 Argon0.0000$27.0017.6M236k2h 6m932
98Qwen3.8-Max0.0000$42.25133.5M1.3M19h 46m4122
99GPT-5.6 Sol0.0000$23.2833.7M166k2h 33m2075
100DeepSeek V4 Flash Vision Exp0.0000$3.44189.2M548k10h 29m4534
101GPT-5.6 Sol0.0000$47.1154.0M192k2h 34m2624
102Gemini 3.8 Flash0.0000$13.11116.9M410k2h 14m3556
103Inkling0.0000$6.496.6M47k1h 53m1421
104Qwen3.8-Max0.0000$56.35191.3M1.2M19h 55m5891
105Grok 4.60.0000$23.0923.9M317k4h 4m1523
106Gemini 3.7 Flash0.0000$3.9124.5M212k1h 28m1552
107Gemini 3.7 Flash0.0000$3.8223.6M220k46m1622
108Inkling0.0000$6.066.2M36k1h 0m1182
109Qwen3.8-Max0.0000$28.3286.1M1.0M14h 43m3863
110DeepSeek V4 Flash Vision Exp0.0000$3.67205.7M547k18h 16m5103

Cranelift Codegen Optimization

task page →109 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.5217$188.61792.1M2.3M19h 20m183619
2Claude Sonnet 5.50.4700$138.58570.3M1.8M19h 30m130910
3Gemini 4 Argon0.4043$256.70491.0M1.5M20h 49m111624
4Claude Opus 5.50.3651$135.88506.9M1.2M19h 1m121734
5Claude Sonnet 5.50.3536$165.14693.2M2.0M18h 53m15353
6Claude Fable 5.10.3484$166.03303.2M604k16h 29m82513
7Claude Fable 5.10.3356$233.87425.4M876k16h 37m102118
8GPT-6 Astra0.3006$2589.931231.7M1.9M19h 38m2587122
9Claude Opus 5.50.2984$145.49543.9M1.3M18h 43m122739
10Claude Opus 50.2915$236.87396.3M962k16h 44m9557
11Claude Fable 5.10.2852$199.91365.0M723k15h 17m97415
12Claude Opus 5.50.2828$138.56513.8M1.3M19h 19m121130
13Claude Sonnet 5.50.2621$131.90545.0M1.7M19h 41m125018
14Claude Fable 50.2501$498.77425.9M919k16h 22m106144
15Claude Opus 5.50.2500$129.78475.1M1.3M18h 48m116227
16GPT-6 Astra0.2357$2732.071287.7M2.4M19h 34m282997
17Gemini 4 Argon0.2201$298.10572.4M2.1M20h 43m125624
18GPT-6 Astra0.2194$2585.691232.6M2.0M18h 22m264379
19Claude Opus 5.50.2063$105.12402.9M850k17h 7m90527
20Claude Fable 5.10.2009$170.71311.4M625k17h 11m81317
21Gemini 4 Argon0.1959$361.37454.4M1.3M17h 22m100227
22Claude Sonnet 5.50.1812$160.59674.3M1.9M17h 6m15134
23Claude Fable 50.1789$444.68370.1M951k17h 14m91822
24GPT-6 Astra0.1650$2812.601334.7M2.3M19h 56m293492
25Claude Opus 50.1550$162.82258.1M858k16h 52m67910
26Claude Haiku 5.50.1347$36.63614.9M2.1M17h 29m14438
27Gemini 4 Argon0.1238$407.04524.2M1.6M20h 47m125528
28Claude Opus 50.1213$221.80357.8M1.1M16h 0m78912
29Claude Opus 50.0902$217.40355.4M1.0M14h 55m89016
30Claude Haiku 5.50.0815$13.27217.3M900k5h 19m5861
31Gemini 3.7 Flash0.0802$35.86231.6M242k6h 15m57420
32Kimi K30.0603$148.59441.7M786k16h 22m102815
33Claude Fable 50.0600$397.22333.0M807k17h 59m85228
34Kimi K30.0478$126.89362.2M801k17h 53m9369
35DeepSeek V4 Flash Vision Exp0.0237$8.27504.6M723k9h 18m126011
36Muse Spark 1.30.0231$411.74433.6M529k18h 32m8754
37Gemini 3.8 Flash0.0215$33.75333.3M357k7h 19m85210
38Muse Spark 1.30.0192$411.77452.6M517k18h 56m9448
39Gemini 3.7 Flash0.0189$20.57157.5M204k2h 49m43217
40GPT-5.6 Sol0.0176$225.59218.6M216k6h 56m5066
41Muse Spark 1.30.0168$495.72581.2M737k19h 59m15303
42GLM-5.30.0162$93.99346.3M474k11h 28m7662
43Claude Haiku 5.50.0152$18.59304.3M1.2M8h 22m6792
44Kimi K30.0132$145.36415.9M1.0M20h 3m10797
45GLM-5.30.0129$109.37311.0M484k17h 22m7709
46Qwen3.8-Max0.0117$41.08108.0M2.2M18h 38m4846
47GLM-5.3 Flash0.0115$9.01238.7M447k10h 39m6794
48Gemini 3.7 Flash0.0110$23.00164.8M188k4h 11m49519
49GLM-5.3 Flash0.0109$12.92356.8M427k14h 26m9584
50DeepSeek V4 Flash Vision Exp0.0107$5.01303.8M439k7h 50m7238
51GLM-5.30.0102$60.68223.7M392k7h 14m6154
52Qwen3.8-Max-09020.0080$64.48159.6M3.9M19h 22m4531
53Gemini 3.8 Flash0.0078$39.55408.0M435k8h 49m102122
54DeepSeek V4 Flash Vision Exp0.0030$5.08311.7M419k8h 3m7816
55Qwen3.8-Max-09020.0007$62.21152.4M3.8M19h 36m5112
56Grok 4.60.0000$113.60103.4M918k9h 35m4266
57Inkling0.0000$8.388.8M12k55m941
58Gemini 3.8 Flash0.0000$49.95454.4M486k9h 11m107517
59Muse Spark 1.30.0000$472.59577.9M275k18h 58m127612
60Grok 4.70.0000$645.99652.2M2.1M20h 0m258915
61GPT-5.6 Sol0.0000$297.21276.6M238k7h 17m5495
62Muse Spark 1.20.0000$33.79127.0M205k10h 23m3565
63Gemini 3.8 Flash0.0000$54.64599.7M676k11h 22m148823
64Claude Haiku 5.50.0000$17.35279.6M1.2M8h 20m6354
65GLM-5.3 Flash0.0000$9.07226.2M412k9h 11m6454
66Qwen3.8-Max-09020.0000$41.4090.2M3.0M20h 1m3622
67Muse Spark 1.20.0000$18.72115.3M194k3h 23m3504
68Qwen3.8-Max0.0000$34.8881.5M2.3M20h 0m4131
69Kimi K30.0000$136.80389.4M1.1M20h 0m100619
70GLM-5.3 Flash0.0000$9.52253.8M421k12h 41m7202
71Claude Opus 50.0000$223.36369.6M980k18h 26m87818
72Qwen3.8-Max-09020.0000$33.0353.9M3.1M20h 1m2631
73Gemini 4 Argon0.0000$212.69506.0M1.7M20h 46m118427
74Gemini 3.7 Flash0.0000$30.61210.1M211k5h 15m59321
75GPT-5.6 Sol0.0000$234.61222.5M240k7h 38m4615
76Qwen3.8-Max-09020.0000$33.1849.8M3.3M20h 0m2601
77Grok 4.60.0000$240.25234.7M1.3M16h 47m89524
78Inkling0.0000$13.7514.4M22k1h 40m1352
79Muse Spark 1.30.0000$394.96454.8M322k15h 45m102112
80Claude Fable 50.0000$391.33323.6M852k17h 7m84924
81Kimi K30.0000$136.72403.0M752k19h 8m114711
82Grok 4.70.0000$228.14230.9M694k6h 44m9487
83Inkling0.0000$11.7912.4M15k1h 2m1211
84Muse Spark 1.20.0000$87.58303.3M711k10h 13m5625
85GPT-5.6 Sol0.0000$212.19205.4M208k5h 52m4615
86Inkling0.0000$8.248.6M21k30m1042
87DeepSeek V4 Flash Vision Exp0.0000$3.68220.8M344k8h 44m6708
88Inkling0.0000$13.8214.5M21k59m1372
89Grok 4.60.0000$138.74131.9M1.2M8h 47m5876
90Gemini 3.8 Flash0.0000$43.81479.7M493k7h 38m115219
91Claude Fable 5.10.0000$232.11427.5M765k16h 0m102335
92Grok 4.70.0000$477.48483.7M1.5M16h 55m197520
93Grok 4.60.0000$138.58127.2M927k7h 29m4889
94Muse Spark 1.20.0000$76.77223.4M655k10h 10m4507
95Muse Spark 1.20.0000$49.18242.6M532k8h 28m4959
96Claude Haiku 5.50.0000$32.91562.1M1.7M19h 9m123314
97Qwen3.8-Max0.0000$43.78119.5M2.2M18h 46m4962
98Qwen3.8-Max0.0000$50.74159.1M1.7M16h 16m6244
99GLM-5.30.0000$110.08353.7M515k18h 43m76118
100Grok 4.70.0000$635.61634.0M1.8M19h 42m254520
101Gemini 3.7 Flash0.0000$47.46341.2M378k8h 44m82822
102GLM-5.3 Flash0.0000$13.40389.9M465k13h 31m9212
103Grok 4.60.0000$108.30103.9M740k6h 37m4476
104DeepSeek V4 Flash Vision Exp0.0000$4.87296.6M422k6h 43m7303
105Claude Fable 50.0000$346.79290.6M710k18h 28m73721
106GLM-5.30.0000$69.79258.7M392k7h 49m7037
107Grok 4.70.0000$640.87669.7M1.8M19h 25m287727
108GPT-5.6 Sol0.0000$355.12344.3M254k10h 32m6273
109Qwen3.8-Max0.0000$42.54115.4M2.2M20h 0m4911

Crash-Proof Flash Filesystem

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.9994$65.32251.2M1.2M7h 54m5079
2Claude Sonnet 5.50.9991$90.59355.9M1.5M17h 4m8246
3Claude Sonnet 5.50.9988$62.92245.6M1.1M10h 2m52211
4Claude Fable 50.9988$187.27145.7M561k6h 17m2948
5Claude Sonnet 5.50.9981$69.13270.2M1.2M18h 11m5764
6Claude Opus 5.50.9981$27.4878.1M449k2h 59m2135
7Claude Opus 5.50.9981$26.9576.7M440k2h 11m2027
8Claude Sonnet 5.50.9978$42.06150.5M930k4h 45m3712
9Claude Opus 5.50.9978$40.02124.8M561k3h 28m2457
10Claude Opus 5.50.9978$56.18167.0M853k5h 25m3758
11Claude Opus 5.50.9978$31.5792.4M498k2h 55m2174
12Claude Opus 50.9977$235.26378.0M1.2M15h 3m81417
13Claude Fable 50.9975$300.62253.7M627k16h 21m45610
14Claude Fable 5.10.9970$49.3477.1M443k2h 57m2086
15Claude Fable 5.10.9927$43.7270.9M340k3h 17m2294
16Claude Fable 5.10.9927$61.85100.4M479k3h 5m24310
17Claude Fable 50.9894$286.95239.2M640k18h 38m4177
18Claude Fable 50.9784$330.54261.4M927k18h 19m64914
19Claude Fable 50.8904$290.91231.9M787k18h 31m5769
20Claude Fable 5.10.8898$81.53137.5M526k5h 0m32610
21Claude Opus 50.8852$226.31360.9M1.2M15h 56m75618
22Claude Opus 50.8705$196.81310.4M1.1M15h 31m68010
23Claude Opus 50.8628$231.46372.7M1.2M17h 30m79416
24Gemini 4 Argon0.7378$152.44168.7M1.1M7h 34m4293
25Claude Opus 50.6631$126.31185.3M890k10h 20m49810
26GPT-6 Astra0.6090$92.2045.6M190k1h 44m1774
27GPT-6 Astra0.5968$497.70237.1M397k4h 16m51614
28GPT-6 Astra0.5902$154.8475.5M253k1h 42m2595
29GPT-6 Astra0.5835$114.9855.8M198k1h 55m2085
30GPT-6 Astra0.5519$228.77111.2M286k2h 11m3325
31Gemini 4 Argon0.5467$54.25127.4M708k4h 23m3002
32Gemini 4 Argon0.2570$245.29429.7M1.7M13h 47m9603
33Claude Haiku 5.50.1981$23.67373.5M1.8M4h 55m8222
34Gemini 4 Argon0.1980$156.36254.9M1.4M8h 56m6242
35Gemini 4 Argon0.1446$77.78221.0M1.0M7h 15m5322
36Grok 4.70.0806$696.28696.9M2.0M12h 34m258417
37Claude Haiku 5.50.0687$47.91775.4M3.3M12h 44m16506
38Grok 4.60.0610$858.44859.7M2.4M19h 46m2990501
39Claude Haiku 5.50.0528$36.17586.2M2.5M9h 44m12384
40Kimi K30.0431$197.20550.4M1.5M20h 1m11971
41Gemini 3.8 Flash0.0394$80.97751.6M1.2M15h 46m169310
42Claude Haiku 5.50.0255$45.61737.3M3.2M16h 38m15728
43Grok 4.60.0241$445.27424.9M2.8M19h 59m1572200
44Gemini 3.8 Flash0.0229$99.02916.4M1.5M20h 0m21362
45GPT-5.6 Sol0.0225$66.2368.5M180k1h 47m2748
46GPT-5.6 Sol0.0225$81.1979.4M199k1h 55m2917
47GPT-5.6 Sol0.0224$73.4072.5M171k1h 41m2738
48Gemini 3.7 Flash0.0217$93.80813.5M2.3M19h 56m21411
49Gemini 3.8 Flash0.0186$116.311099.4M1.7M19h 58m26581
50Gemini 3.8 Flash0.0186$181.151820.6M3.3M20h 0m43832
51Grok 4.70.0184$312.58313.6M1.2M9h 0m128010
52Grok 4.70.0184$793.49801.3M2.8M20h 0m308423
53Muse Spark 1.30.0177$523.70619.4M1.1M20h 0m14091
54Claude Fable 5.10.0173$56.4490.9M453k4h 18m2288
55Grok 4.70.0173$406.03410.3M1.5M9h 50m162419
56GPT-5.6 Sol0.0173$159.04153.2M259k4h 31m44016
57GPT-5.6 Sol0.0173$92.7287.0M212k1h 59m2687
58GLM-5.30.0173$171.41627.5M1.2M19h 32m138514
59Muse Spark 1.30.0173$532.50628.8M1.0M20h 0m15521
60GLM-5.30.0173$236.98874.4M1.4M19h 51m190831
61Claude Haiku 5.50.0173$35.40562.3M2.6M7h 29m11855
62Grok 4.70.0164$349.50343.9M1.4M11h 51m13498
63Grok 4.60.0117$262.00255.9M1.7M13h 11m103920
64Kimi K30.0112$202.76569.3M1.5M19h 50m12372
65Gemini 3.7 Flash0.0112$89.95756.9M1.7M20h 0m19071
66GLM-5.30.0111$148.21526.6M1.0M18h 49m117516
67DeepSeek V4 Flash Vision Exp0.0110$29.121761.2M2.9M19h 19m391124
68Qwen3.8-Max-09020.0057$36.0358.6M3.4M19h 58m2711
69DeepSeek V4 Flash Vision Exp0.0053$22.611343.5M2.5M19h 20m286726
70GLM-5.30.0049$108.31386.0M1.3M16h 54m8515
71DeepSeek V4 Flash Vision Exp0.0049$20.651205.0M2.5M19h 56m249819
72GLM-5.3 Flash0.0049$18.82518.9M1.2M16h 54m12277
73Muse Spark 1.20.0049$36.55207.9M989k3h 16m45611
74Kimi K30.0049$158.40411.0M1.7M20h 0m10101
75GLM-5.3 Flash0.0049$17.24495.9M945k18h 11m12227
76DeepSeek V4 Flash Vision Exp0.0049$17.941097.8M1.6M18h 58m234814
77Gemini 3.7 Flash0.0049$62.15472.1M1.5M20h 0m11391
78DeepSeek V4 Flash Vision Exp0.0049$20.781251.0M2.1M19h 4m280415
79Kimi K30.0049$190.49508.0M1.5M19h 54m11119
80GLM-5.3 Flash0.0049$25.92740.1M1.3M17h 17m146914
81GLM-5.3 Flash0.0047$19.42522.2M1.2M17h 11m12305
82Muse Spark 1.20.0047$53.94336.5M554k4h 31m6607
83Grok 4.60.0046$267.41252.9M1.7M10h 33m927132
84GLM-5.30.0039$154.89566.6M1.0M19h 45m135018
85Muse Spark 1.20.0038$13.6058.8M346k1h 50m1893
86Muse Spark 1.20.0033$35.75222.8M379k2h 39m4897
87Grok 4.60.0031$181.59175.3M1.4M8h 20m69324
88Gemini 3.7 Flash0.0024$124.701220.5M2.9M20h 0m27951
89Qwen3.8-Max0.0013$12.1816.0M1.3M19h 33m1301
90Gemini 3.8 Flash0.0013$151.241551.3M2.4M20h 0m36131
91Gemini 3.7 Flash0.0010$64.73520.0M1.4M20h 0m13561
92Qwen3.8-Max-09020.0008$39.7967.5M3.7M19h 56m2756
93Qwen3.8-Max-09020.0008$36.6160.3M3.5M20h 1m2942
94Kimi K30.0008$195.88529.5M1.7M20h 0m12662
95GLM-5.3 Flash0.0008$18.99548.2M1.2M18h 12m117211
96Qwen3.8-Max-09020.0008$33.7844.2M3.7M20h 1m2261
97Qwen3.8-Max-09020.0006$33.0143.7M3.6M20h 1m2361
98Muse Spark 1.30.0002$572.11638.9M1.2M19h 59m13841
99Qwen3.8-Max0.0001$13.8119.3M1.5M19h 35m1643
100Qwen3.8-Max0.0000$14.3919.8M1.5M20h 1m1601
101Inkling0.0000$14.1614.7M37k1h 30m1842
102Muse Spark 1.30.0000$486.57544.5M845k19h 59m14211
103Qwen3.8-Max0.0000$9.1810.7M1.0M19h 50m1001
104Inkling0.0000$9.309.7M22k11m1232
105Muse Spark 1.30.0000$536.44601.3M1.3M19h 59m13241
106Inkling0.0000$12.0812.6M23k14m1612
107Qwen3.8-Max0.0000$13.7218.7M1.5M18h 42m1463
108Muse Spark 1.20.0000$18.5097.7M207k1h 10m2694
109Inkling0.0000$16.4517.2M21k16m1732
110Inkling0.0000$13.1713.7M28k1h 27m1862

Dart Style in Haskell

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9894$168.41622.4M1.6M10h 59m138939
2Claude Opus 5.50.9885$192.52720.9M1.8M13h 2m167053
3Claude Opus 5.50.9853$159.11577.5M1.6M9h 35m133818
4Claude Opus 5.50.9829$190.35691.9M2.0M9h 34m160224
5Claude Opus 5.50.9733$318.711272.8M2.4M16h 51m286899
6Claude Sonnet 5.50.9726$294.321267.9M3.1M19h 20m276715
7Gemini 4 Argon0.9654$218.42430.1M2.0M15h 3m101021
8Claude Sonnet 5.50.9628$264.231140.1M2.8M19h 20m238618
9GPT-6 Astra0.9601$2439.091157.2M2.2M16h 56m267130
10Claude Sonnet 5.50.9599$231.53982.7M2.7M19h 6m20998
11Claude Sonnet 5.50.9594$281.271200.2M3.2M19h 38m267525
12Gemini 4 Argon0.9568$288.60454.6M2.0M16h 22m109314
13Gemini 4 Argon0.9534$274.81581.3M2.0M17h 49m136815
14Gemini 4 Argon0.9529$147.73628.9M2.2M16h 46m147823
15GPT-6 Astra0.9508$2034.34972.8M1.7M15h 13m221642
16Claude Fable 5.10.9491$569.861069.9M1.4M17h 10m228528
17Claude Sonnet 5.50.9484$282.691214.1M3.1M19h 50m271218
18GPT-6 Astra0.9472$895.41422.2M827k6h 22m95814
19Gemini 4 Argon0.9457$337.69476.2M2.1M17h 14m105518
20GPT-6 Astra0.9426$2766.391322.7M2.4M19h 53m298474
21Claude Fable 5.10.9284$552.061031.1M1.5M18h 56m209146
22Claude Fable 5.10.9275$456.14848.4M1.3M18h 57m202639
23Claude Opus 50.8972$636.781144.6M1.6M19h 47m23834
24GPT-6 Astra0.8965$171.4681.1M258k2h 1m2777
25Claude Fable 5.10.8919$415.43774.8M1.2M19h 19m179647
26Claude Fable 50.8720$1092.68955.8M1.8M19h 38m203716
27Claude Fable 5.10.8712$313.43577.0M1.0M18h 15m128312
28Claude Opus 50.8643$420.46752.1M1.2M19h 22m15365
29Claude Fable 50.8484$882.98764.1M1.5M19h 42m184023
30Claude Opus 50.8376$279.11485.1M948k19h 29m11963
31Claude Haiku 5.50.8374$77.491375.8M3.3M18h 52m294236
32Claude Fable 50.8275$664.26571.5M1.2M19h 26m119710
33Claude Opus 50.8261$296.13517.9M961k18h 59m127726
34Claude Opus 50.8114$315.87552.3M1.0M19h 44m126218
35Claude Fable 50.8095$644.11555.7M1.2M19h 31m123715
36Claude Haiku 5.50.8018$62.961119.5M2.6M19h 39m250241
37Claude Haiku 5.50.7992$77.731399.9M2.9M18h 46m299420
38GPT-5.6 Sol0.7949$998.14972.7M983k19h 18m214616
39Claude Fable 50.7696$331.51264.9M908k19h 45m6372
40Grok 4.70.7672$810.72832.8M2.4M19h 51m3315144
41Claude Haiku 5.50.7663$58.711042.8M2.4M19h 8m219217
42Claude Haiku 5.50.7528$39.53699.1M1.7M19h 36m150718
43Grok 4.70.7101$934.33959.7M2.7M20h 0m378676
44Grok 4.70.6935$819.81827.3M2.4M19h 30m329279
45Grok 4.70.6906$879.91896.0M2.8M19h 59m356182
46GPT-5.6 Sol0.6779$433.00423.6M391k6h 1m8444
47Gemini 3.8 Flash0.6582$120.091254.6M1.6M19h 48m2946161
48Gemini 3.7 Flash0.6517$199.282123.1M2.6M19h 55m491762
49GPT-5.6 Sol0.6344$89.8091.5M201k1h 55m3625
50Muse Spark 1.20.6241$2.2911.0M77k1h 6m1283
51Gemini 3.8 Flash0.6130$135.281312.0M1.7M19h 37m2953110
52GPT-5.6 Sol0.6068$48.4752.9M204k1h 35m2743
53Grok 4.60.5864$513.86512.7M2.7M20h 0m205459
54Kimi K30.5650$209.81607.6M1.3M20h 1m145419
55Muse Spark 1.30.5513$525.73756.2M1.1M19h 57m16378
56Kimi K30.5395$190.44541.2M1.2M19h 50m13363
57Gemini 3.7 Flash0.5376$121.241110.9M1.5M19h 27m252437
58GLM-5.30.5299$165.74599.8M1.1M19h 6m139851
59Muse Spark 1.30.5258$522.21631.2M1.1M19h 59m17575
60Muse Spark 1.30.5020$463.61501.9M1.1M19h 20m12659
61Gemini 3.8 Flash0.4900$51.76544.5M634k8h 8m124124
62Kimi K30.4874$196.59547.1M1.3M19h 46m12418
63Qwen3.8-Max0.4828$83.97303.2M1.2M16h 38m8932
64GLM-5.30.4696$158.77595.9M645k19h 33m117712
65GLM-5.30.4653$144.84516.1M611k19h 39m106622
66GLM-5.30.4595$150.71560.0M706k19h 32m126335
67GPT-5.6 Sol0.4547$71.7984.5M237k2h 25m4067
68Gemini 3.7 Flash0.4365$75.56629.3M934k19h 55m13313
69Grok 4.70.4324$263.14264.6M900k6h 3m99620
70Kimi K30.4305$123.27338.1M738k19h 52m6701
71Gemini 3.7 Flash0.4242$33.92324.0M891k3h 25m7808
72GLM-5.3 Flash0.4031$18.46598.3M640k20h 1m12001
73DeepSeek V4 Flash Vision Exp0.4014$18.121122.6M1.6M19h 51m260223
74GLM-5.3 Flash0.4009$22.72722.1M1.2M19h 26m166727
75GLM-5.30.3788$98.82359.7M600k20h 0m7381
76Muse Spark 1.30.3680$506.26577.2M925k19h 53m15671
77GLM-5.3 Flash0.3666$15.53455.8M658k20h 1m8641
78Qwen3.8-Max0.3212$156.83579.3M1.7M20h 1m15061
79Gemini 3.7 Flash0.3137$25.24282.5M578k1h 28m5902
80Grok 4.60.3015$389.00386.7M2.2M19h 53m164542
81Qwen3.8-Max-09020.2762$68.64209.5M2.5M19h 58m6501
82Qwen3.8-Max0.2726$83.47304.6M1.0M17h 28m8432
83Qwen3.8-Max0.2674$50.86177.6M941k18h 25m66212
84DeepSeek V4 Flash Vision Exp0.2342$7.03436.2M602k8h 13m9143
85DeepSeek V4 Flash Vision Exp0.2234$21.231304.8M2.0M15h 38m28367
86GLM-5.3 Flash0.2155$15.10395.1M560k20h 1m8511
87Qwen3.8-Max-09020.1979$53.96142.4M2.8M19h 56m4441
88Grok 4.60.1785$547.31552.2M2.4M19h 52m217774
89Gemini 3.8 Flash0.1718$3.0222.3M97k43m1983
90DeepSeek V4 Flash Vision Exp0.1638$15.31956.5M1.3M19h 4m20233
91GLM-5.3 Flash0.1396$17.07519.3M626k20h 0m10151
92Gemini 3.8 Flash0.1167$2.1314.3M77k33m1762
93Muse Spark 1.20.1043$2.539.5M123k1h 21m1011
94Muse Spark 1.20.1040$2.1810.0M104k1h 4m1132
95Muse Spark 1.20.1040$3.4116.0M109k59m1102
96Qwen3.8-Max0.0853$104.77373.0M1.7M19h 28m9571
97DeepSeek V4 Flash Vision Exp0.0766$15.69953.5M1.5M16h 48m21995
98Qwen3.8-Max-09020.0514$56.12143.5M3.2M20h 2m4931
99Muse Spark 1.20.0377$5.5530.5M146k1h 16m1742
100Muse Spark 1.30.0010$582.91707.6M1.1M19h 56m174010
101Inkling0.0000$2.953.1M10k11m872
102Inkling0.0000$20.4921.4M45k32m2411
103Qwen3.8-Max-09020.0000$93.37320.2M1.9M20h 1m7552
104Grok 4.60.0000$485.05493.3M2.2M19h 52m1992109
105Qwen3.8-Max-09020.0000$44.9792.5M2.9M20h 1m5111
106Grok 4.60.0000$402.09394.7M2.1M17h 23m152478
107Inkling0.0000$19.8820.7M49k1h 2m2971
108Inkling0.0000$7.808.1M20k1h 3m1401
109Inkling0.0000$4.624.8M11k1h 10m1012
110Kimi K30.0000$86.57238.4M589k20h 1m5931

FFmpeg libswscale Optimization

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.8444$169.75555.3M2.2M12h 14m123042
2Claude Fable 5.10.8080$283.04487.0M1.6M13h 9m107046
3Claude Sonnet 5.50.5593$210.44829.8M3.5M18h 18m166232
4Claude Fable 5.10.5509$202.06343.4M1.3M9h 13m81928
5Claude Sonnet 5.50.5128$191.15731.8M3.5M16h 45m154918
6Claude Fable 5.10.5106$148.93254.0M906k6h 11m64118
7Claude Fable 50.3296$651.27511.9M1.9M17h 29m109944
8GPT-6 Astra0.2755$169.8582.4M307k2h 7m2907
9Claude Opus 50.2730$386.74584.2M2.5M17h 26m123648
10Claude Opus 50.2685$323.38505.1M1.9M18h 50m105536
11Claude Haiku 5.50.2461$32.33512.1M2.4M8h 34m11749
12Claude Fable 50.2400$694.93559.7M1.8M18h 56m122665
13Claude Opus 50.2348$359.20577.0M1.9M15h 26m119024
14Claude Fable 50.2293$457.04364.2M1.2M18h 33m75837
15Claude Haiku 5.50.2204$29.73450.8M2.6M7h 6m9962
16Claude Opus 50.2127$514.92809.2M2.9M17h 33m176045
17GPT-6 Astra0.2021$313.12153.5M377k2h 54m4589
18GPT-6 Astra0.1983$306.45149.1M351k2h 48m4448
19Claude Opus 50.1899$481.68774.7M2.5M14h 53m159254
20GLM-5.30.1752$226.40818.4M2.0M19h 33m188418
21GPT-6 Astra0.1741$262.36125.2M349k2h 37m3796
22Claude Fable 50.1712$501.72411.4M1.2M18h 49m87742
23Claude Haiku 5.50.1587$30.27466.6M2.5M11h 4m107217
24Gemini 4 Argon0.1572$160.32346.6M1.9M11h 31m76513
25Claude Fable 50.1436$530.26432.3M1.3M19h 40m86428
26GLM-5.30.1410$148.35524.2M1.7M16h 26m13038
27GLM-5.30.1369$139.76505.8M1.2M11h 14m10979
28Claude Fable 5.10.1368$219.11385.2M1.1M10h 27m83522
29Muse Spark 1.30.1277$499.70617.7M951k19h 17m140124
30GLM-5.3 Flash0.1268$16.00489.1M1.2M13h 53m1179110
31Kimi K30.1260$127.79342.6M1.2M13h 59m82713
32Kimi K30.1252$211.22606.6M1.4M19h 43m13823
33GLM-5.30.1231$175.55619.5M1.7M16h 47m15098
34Claude Opus 5.50.1224$83.47264.7M1.1M5h 11m54914
35Claude Opus 5.50.1185$175.12575.5M2.3M11h 51m120346
36GPT-6 Astra0.1179$275.12132.2M355k2h 35m3966
37Muse Spark 1.30.1028$438.57557.6M1.0M16h 30m134023
38Claude Sonnet 5.50.1012$189.51720.9M3.5M18h 17m153835
39Muse Spark 1.30.1003$186.76239.3M502k7h 59m55914
40Muse Spark 1.30.0996$157.06200.2M465k6h 34m50412
41GLM-5.3 Flash0.0819$11.44312.2M1.0M11h 47m7862
42Kimi K30.0799$127.97356.2M1.1M15h 4m91411
43GLM-5.30.0783$177.95625.3M1.7M17h 1m14208
44Muse Spark 1.30.0779$279.58336.6M595k9h 26m68817
45Claude Haiku 5.50.0742$11.46167.4M1.1M3h 2m4214
46GLM-5.3 Flash0.0721$12.54348.2M1.1M9h 45m8384
47Grok 4.70.0717$958.45972.7M3.5M19h 0m381051
48GLM-5.3 Flash0.0710$14.74418.0M1.0M13h 2m9636
49Claude Sonnet 5.50.0703$164.01627.4M3.0M15h 19m126823
50Grok 4.70.0692$75.9476.6M393k2h 13m3495
51DeepSeek V4 Flash Vision Exp0.0668$8.52493.3M1.0M6h 44m10958
52Kimi K30.0639$138.03382.3M1.1M17h 32m9022
53DeepSeek V4 Flash Vision Exp0.0636$9.11528.7M1.1M6h 10m11725
54DeepSeek V4 Flash Vision Exp0.0602$13.77800.3M1.6M9h 14m183119
55GLM-5.3 Flash0.0591$10.52294.6M1.1M15h 39m7681
56Grok 4.70.0562$84.2786.0M423k2h 12m3535
57DeepSeek V4 Flash Vision Exp0.0483$9.39554.1M1.0M5h 54m119716
58Grok 4.70.0482$1089.411092.6M3.0M15h 42m392949
59Claude Sonnet 5.50.0471$76.69272.4M1.7M6h 51m6129
60Claude Opus 5.50.0441$106.98317.9M1.6M6h 52m69318
61Gemini 3.8 Flash0.0421$22.33232.8M629k2h 36m6568
62Qwen3.8-Max0.0373$86.44286.2M2.3M17h 43m7066
63Grok 4.60.0360$419.25404.2M2.4M19h 56m1517114
64Qwen3.8-Max0.0181$64.05193.9M2.4M18h 48m5551
65Gemini 3.7 Flash0.0125$20.83184.0M617k2h 35m5242
66Qwen3.8-Max0.0053$46.03124.6M2.3M19h 58m4241
67Gemini 3.7 Flash0.0032$19.94167.8M795k2h 4m4967
68Grok 4.70.0022$90.4689.2M451k3h 23m3799
69Grok 4.60.0000$1121.421126.0M2.4M18h 11m3693434
70Muse Spark 1.20.0000$15.4290.0M327k41m2862
71Grok 4.60.0000$68.4059.6M603k3h 50m2294
72Muse Spark 1.20.0000$16.9785.6M384k1h 38m2274
73Gemini 3.8 Flash0.0000$23.73247.4M548k2h 37m6743
74Claude Fable 5.10.0000$217.24363.8M1.5M10h 22m89327
75Gemini 4 Argon0.0000$156.84296.0M1.6M9h 55m66811
76Gemini 4 Argon0.0000$106.17273.4M1.3M8h 28m60517
77Qwen3.8-Max0.0000$54.69158.2M2.4M18h 58m4751
78Grok 4.60.0000$132.56129.2M778k5h 28m56227
79Inkling0.0000$11.2411.7M27k1h 20m1652
80Inkling0.0000$15.4516.1M35k22m1882
81Gemini 3.8 Flash0.0000$19.00192.6M496k2h 5m5364
82Qwen3.8-Max-09020.0000$39.6168.0M3.6M20h 1m2751
83Qwen3.8-Max0.0000$30.1266.3M2.1M19h 55m2981
84Inkling0.0000$39.6641.4M77k41m3542
85Gemini 3.7 Flash0.0000$25.27228.2M1.1M2h 14m6555
86GPT-5.6 Sol0.0000$66.8275.1M179k1h 59m3188
87Gemini 3.8 Flash0.0000$31.46339.3M663k5h 43m88117
88Qwen3.8-Max-09020.0000$44.8472.8M3.4M20h 2m3451
89Inkling0.0000$15.5116.2M36k32m1901
90Muse Spark 1.20.0000$11.9064.7M340k1h 14m2232
91GPT-5.6 Sol0.0000$78.4384.8M190k2h 4m3485
92Grok 4.60.0000$380.75368.6M1.8M11h 52m137067
93Muse Spark 1.20.0000$35.70203.8M978k3h 29m4688
94Claude Haiku 5.50.0000$13.45205.4M1.1M2h 38m4883
95GPT-5.6 Sol0.0000$123.31124.9M233k2h 12m4223
96Kimi K30.0000$171.14500.1M1.1M19h 41m117547
97Qwen3.8-Max-09020.0000$51.17115.3M3.5M20h 1m3581
98Claude Opus 5.50.0000$168.91529.9M2.4M15h 41m115037
99GPT-5.6 Sol0.0000$76.6786.4M186k3h 5m36910
100Gemini 4 Argon0.0000$58.88167.7M1.1M5h 59m4057
101Qwen3.8-Max-09020.0000$43.4382.1M3.6M20h 1m3061
102DeepSeek V4 Flash Vision Exp0.0000$12.34718.0M1.4M8h 32m167816
103GPT-5.6 Sol0.0000$117.96120.8M233k3h 42m4058
104Inkling0.0000$11.1711.6M27k16m1671
105Qwen3.8-Max-09020.0000$72.15209.7M3.0M19h 38m5431
106Gemini 4 Argon0.0000$190.93224.2M1.2M7h 43m5318
107Gemini 3.8 Flash0.0000$22.37231.7M581k2h 9m68312
108Gemini 3.7 Flash0.0000$16.99131.7M937k2h 45m4486
109Muse Spark 1.20.0000$27.98159.1M568k1h 40m3452
110Gemini 3.7 Flash0.0000$44.74251.9M922k8h 1m7586

Fitness-Recap Video in Remotion

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.7901$2673.961271.2M2.5M19h 58m299131
2GPT-6 Astra0.7705$2639.521259.7M2.5M19h 50m296127
3GPT-6 Astra0.7148$2733.411304.4M2.5M19h 53m297729
4GPT-6 Astra0.6873$2846.471353.6M2.5M19h 54m311436
5GPT-6 Astra0.6437$2584.511240.4M2.4M19h 47m292023
6Claude Sonnet 5.50.3659$232.86951.4M2.7M19h 46m21883
7Claude Opus 5.50.3605$270.941051.2M2.1M19h 10m240312
8Claude Fable 50.3226$587.70496.9M1.2M18h 28m11188
9Claude Sonnet 5.50.3212$193.06791.5M2.2M19h 6m17181
10Claude Sonnet 5.50.3201$185.52762.3M2.2M19h 19m17242
11Claude Sonnet 5.50.3192$216.22909.3M2.5M19h 44m20302
12Claude Opus 5.50.2926$307.931148.9M1.9M19h 20m255328
13Claude Opus 5.50.2905$179.59686.0M1.3M19h 22m164521
14Claude Sonnet 5.50.2754$168.83706.6M2.1M19h 28m16793
15Claude Opus 5.50.2637$181.24683.8M1.4M19h 15m166719
16Gemini 4 Argon0.2451$233.36596.2M1.7M16h 49m126012
17Claude Opus 5.50.2443$84.28312.7M521k9h 32m66010
18Gemini 4 Argon0.2401$112.07365.5M1.1M10h 13m8605
19Claude Haiku 5.50.2316$28.48497.9M1.3M13h 17m10858
20Claude Opus 50.2280$444.54757.9M1.7M18h 35m164423
21Claude Opus 50.2251$524.60906.1M1.9M19h 37m194917
22Gemini 4 Argon0.2185$165.03335.8M998k11h 8m8052
23Claude Haiku 5.50.2169$33.38569.6M1.7M9h 44m13006
24Claude Fable 50.2168$885.34754.4M1.7M18h 17m172116
25Claude Opus 50.2158$509.67881.7M1.8M18h 48m18528
26Claude Opus 50.2155$438.52750.5M1.6M18h 17m164814
27GPT-5.6 Sol0.2152$950.51938.4M1.0M19h 3m234345
28Claude Opus 50.2129$501.05832.6M1.6M18h 19m191214
29Gemini 4 Argon0.2055$210.50290.4M915k10h 7m7172
30Claude Fable 5.10.2055$157.69293.5M491k6h 51m6658
31Claude Fable 50.2027$655.49552.4M1.4M18h 20m120314
32Claude Fable 5.10.2018$157.38293.1M476k6h 7m6447
33Gemini 4 Argon0.1980$159.82263.8M756k8h 13m6363
34Claude Haiku 5.50.1957$25.71439.2M1.3M6h 34m9475
35GPT-5.6 Sol0.1930$656.93636.3M650k19h 12m147811
36Claude Fable 5.10.1927$120.12223.7M414k5h 14m5877
37GPT-5.6 Sol0.1913$298.28288.7M261k7h 23m65112
38GPT-5.6 Sol0.1895$283.99275.5M274k5h 43m6876
39GLM-5.30.1894$78.50212.7M442k18h 20m5306
40Claude Haiku 5.50.1842$16.30276.2M923k15h 8m66611
41GLM-5.30.1828$113.14407.8M483k19h 2m8049
42Muse Spark 1.30.1827$179.291045.0M1.1M19h 56m22908
43Kimi K30.1767$191.75571.0M982k19h 53m13563
44GLM-5.3 Flash0.1750$19.23554.0M928k19h 35m13941
45Claude Fable 5.10.1730$560.601048.2M1.5M18h 2m227426
46Kimi K30.1723$171.83504.1M1.1M19h 44m12348
47Kimi K30.1716$266.42802.2M1.3M20h 1m16181
48Claude Haiku 5.50.1704$8.47145.8M443k15h 41m4199
49GLM-5.3 Flash0.1702$12.92416.9M481k11h 49m10025
50DeepSeek V4 Flash Vision Exp0.1621$10.73658.6M994k19h 13m165118
51Qwen3.8-Max-09020.1486$33.4889.8M1.0M20h 8m4102
52Qwen3.8-Max0.1474$77.77271.1M994k13h 7m8004
53Claude Fable 50.1467$662.31571.3M1.2M19h 23m122112
54Qwen3.8-Max-09020.1462$31.9568.8M1.2M20h 2m3511
55GLM-5.30.1426$118.44380.0M784k18h 55m98618
56GPT-5.6 Sol0.1374$190.12189.9M230k5h 21m5892
57Muse Spark 1.30.1338$375.85806.9M1.0M20h 0m19273
58Claude Fable 50.1112$587.97497.7M1.2M19h 20m109410
59GLM-5.30.1053$110.52388.9M908k15h 36m9619
60GLM-5.3 Flash0.1000$22.01692.4M913k17h 25m16356
61Grok 4.70.0961$439.29445.6M1.3M9h 16m1738103
62GLM-5.3 Flash0.0914$16.05372.4M537k19h 9m8283
63Grok 4.70.0840$675.93699.4M1.7M12h 52m279089
64GLM-5.30.0837$90.93307.2M485k16h 10m6368
65DeepSeek V4 Flash Vision Exp0.0738$6.53405.2M565k19h 26m99410
66Qwen3.8-Max0.0733$163.48458.4M1.7M19h 54m12491
67Claude Fable 5.10.0694$335.29627.1M960k15h 45m145619
68Kimi K30.0657$243.01727.7M1.1M20h 1m16331
69Kimi K30.0536$202.63587.9M1.0M19h 57m147912
70Grok 4.70.0491$750.66786.8M2.0M15h 22m3238130
71DeepSeek V4 Flash Vision Exp0.0483$6.64411.0M525k16h 0m98321
72Grok 4.70.0481$814.19833.8M1.7M19h 58m3225109
73Grok 4.70.0422$931.62946.8M1.9M20h 0m3560153
74GLM-5.3 Flash0.0395$21.46680.4M950k19h 31m161312
75Muse Spark 1.30.0362$213.98610.8M874k19h 50m16363
76Grok 4.60.0338$1762.941204.0M2.8M20h 0m4175289
77DeepSeek V4 Flash Vision Exp0.0324$12.46767.8M1.1M18h 4m178924
78Qwen3.8-Max-09020.0314$43.03134.8M748k20h 9m4051
79Grok 4.60.0279$646.10557.5M1.5M19h 48m2043149
80Muse Spark 1.30.0269$429.57453.8M790k19h 52m12452
81Muse Spark 1.30.0263$363.14496.5M863k19h 59m13371
82Grok 4.60.0245$555.19490.3M1.5M19h 56m202090
83Grok 4.60.0242$1149.83792.5M1.8M19h 58m2836250
84Gemini 3.8 Flash0.0241$38.64291.2M430k9h 43m8663
85Grok 4.60.0216$746.94531.5M1.4M19h 55m1941163
86Gemini 3.7 Flash0.0129$13.97114.7M211k4h 23m3822
87Qwen3.8-Max0.0127$196.38482.4M1.8M19h 51m10481
88DeepSeek V4 Flash Vision Exp0.0121$4.01242.4M395k12h 19m77716
89Gemini 3.7 Flash0.0091$2.9421.2M86k1h 20m1692
90Gemini 3.7 Flash0.0089$10.4467.7M164k2h 48m3284
91Gemini 3.7 Flash0.0080$7.6861.7M148k2h 7m3001
92Muse Spark 1.20.0079$12.4662.2M180k3h 28m2703
93Qwen3.8-Max0.0062$52.83157.6M675k9h 28m5784
94Muse Spark 1.20.0060$91.70184.1M1.3M8h 42m5093
95Gemini 3.7 Flash0.0060$4.6730.1M112k2h 7m2221
96Qwen3.8-Max-09020.0051$35.2296.8M1.1M20h 1m3421
97Muse Spark 1.20.0032$14.7129.2M224k3h 30m1832
98Muse Spark 1.20.0031$37.8575.3M303k4h 52m2854
99Qwen3.8-Max-09020.0029$28.3169.9M1.1M20h 5m3551
100Inkling0.0006$14.0514.6M38k1h 0m1831
101Inkling0.0001$7.968.3M26k31m1412
102Gemini 3.8 Flash0.0000†$3.2119.3M43k1h 20m1601
103Gemini 3.8 Flash0.0000†$3.9527.7M51k1h 46m1831
104Inkling0.0000$13.7214.2M49k59m2051
105Inkling0.0000$10.6511.1M29k1h 18m1722
106Inkling0.0000$11.1511.6M44k40m1381
107Qwen3.8-Max0.0000†$11.9131.2M238k4h 2m2922
108Muse Spark 1.20.0000†$12.6638.1M209k4h 41m1901
109Gemini 3.8 Flash0.0000†$1.7310.5M40k42m1051
110Gemini 3.8 Flash0.0000†$4.9231.8M62k1h 28m2131

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Flight-Sim Renderer in OpenGL

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.9965$2541.331210.9M2.5M19h 50m283027
2GPT-6 Astra0.9845$2685.881278.3M2.6M20h 0m296138
3GPT-6 Astra0.9844$2735.711297.4M2.6M19h 42m288429
4GPT-6 Astra0.9841$2589.721228.2M2.6M19h 59m280134
5GPT-6 Astra0.9841$2728.191288.8M2.7M19h 57m294147
6Gemini 4 Argon0.9334$206.78382.0M1.3M15h 47m8775
7Claude Opus 5.50.9097$156.04545.9M1.3M19h 52m128819
8Claude Sonnet 5.50.9083$181.73740.0M2.3M18h 47m15466
9Gemini 4 Argon0.9080$207.90379.4M1.5M15h 34m85410
10Claude Sonnet 5.50.8981$169.21677.4M2.4M19h 40m15494
11Claude Opus 5.50.8821$144.22511.3M1.0M18h 11m107426
12Claude Opus 5.50.8618$140.79553.3M1.1M19h 44m11914
13Claude Opus 5.50.8540$182.36671.0M1.3M19h 5m163723
14Gemini 4 Argon0.8458$261.90442.3M1.8M19h 2m10566
15Claude Sonnet 5.50.7941$169.89694.5M2.3M19h 11m15802
16Gemini 4 Argon0.7148$130.35185.9M816k8h 32m4493
17Gemini 4 Argon0.7072$170.81258.5M1.2M8h 45m6733
18Claude Sonnet 5.50.7057$164.69656.9M2.0M19h 44m15666
19Claude Sonnet 5.50.6877$201.48823.9M2.7M19h 38m18978
20Claude Opus 5.50.6632$158.77603.5M1.1M18h 8m12037
21Claude Fable 5.10.4716$208.91376.5M866k17h 50m101710
22Claude Fable 5.10.3532$168.41314.0M539k12h 53m6084
23Claude Fable 5.10.3481$106.70193.6M429k9h 8m45413
24Claude Fable 5.10.3402$125.75229.9M473k10h 25m4826
25Claude Opus 50.2471$159.25261.3M595k19h 14m5303
26GPT-5.6 Sol0.2171$270.86274.0M362k12h 30m8064
27Claude Haiku 5.50.2045$31.05511.9M1.8M18h 49m11383
28Claude Opus 50.2039$238.32344.9M699k19h 25m73512
29Claude Fable 5.10.1985$113.40205.2M463k5h 28m4303
30Claude Fable 50.1934$427.55353.3M996k18h 35m9243
31Claude Haiku 5.50.1872$31.43521.7M1.9M17h 21m11525
32Claude Opus 50.1567$190.60308.2M776k19h 30m7425
33GPT-5.6 Sol0.1552$336.67340.6M347k11h 28m90614
34Claude Fable 50.1550$396.50323.2M982k19h 5m8487
35Grok 4.70.1336$487.10480.1M1.3M20h 1m183777
36Claude Fable 50.1319$351.84291.9M807k19h 38m7118
37Claude Opus 50.1302$226.32342.2M722k19h 35m76014
38GPT-5.6 Sol0.1222$253.61257.1M305k8h 28m7603
39Grok 4.70.1182$509.72506.8M1.5M18h 52m206885
40Grok 4.70.1138$588.60597.8M1.8M19h 55m2409106
41GPT-5.6 Sol0.1119$309.74312.3M342k9h 22m85712
42Muse Spark 1.30.1055$206.91689.2M886k10h 35m16811
43GPT-5.6 Sol0.1032$420.32406.2M354k11h 35m88013
44Claude Fable 50.0950$314.88250.5M673k18h 55m4847
45Claude Haiku 5.50.0884$18.09294.8M1.2M8h 15m6824
46Claude Haiku 5.50.0726$19.59319.7M1.3M12h 4m7105
47Grok 4.70.0713$540.56547.5M1.5M19h 14m2247102
48Grok 4.60.0526$317.62274.4M1.8M19h 55m1078110
49Muse Spark 1.30.0410$299.15649.2M932k19h 37m15882
50Muse Spark 1.30.0386$233.75628.1M517k18h 2m12825
51Grok 4.60.0382$286.38260.8M1.4M19h 57m984103
52Gemini 3.8 Flash0.0349$41.18386.0M562k10h 22m9704
53Grok 4.60.0273$488.84437.7M2.0M19h 56m1536307
54Grok 4.60.0266$454.46403.4M2.0M19h 58m143575
55Muse Spark 1.30.0254$147.68673.6M1.0M19h 47m15618
56Muse Spark 1.30.0250$351.72511.0M807k19h 59m13001
57Kimi K30.0249$126.07350.4M1.1M19h 56m9367
58Claude Opus 50.0249$181.57297.4M666k19h 31m6026
59Kimi K30.0214$168.60476.4M1.3M20h 1m10795
60Grok 4.70.0196$518.13515.0M1.7M19h 40m207958
61GLM-5.30.0166$91.30316.9M852k19h 35m8917
62Grok 4.60.0147$328.36283.8M1.8M19h 57m108457
63Claude Haiku 5.50.0140$10.65174.9M638k2h 59m3515
64Gemini 3.8 Flash0.0130$23.89196.2M401k6h 33m5073
65Gemini 3.7 Flash0.0116$11.2868.7M237k4h 7m3042
66Kimi K30.0104$167.00460.9M1.4M20h 1m10391
67Gemini 3.8 Flash0.0089$32.30275.0M453k6h 8m6104
68Kimi K30.0079$184.18516.4M1.3M19h 37m10942
69DeepSeek V4 Flash Vision Exp0.0069$10.96663.9M1.1M19h 2m15272
70DeepSeek V4 Flash Vision Exp0.0065$10.60633.4M1.1M15h 56m15168
71Gemini 3.7 Flash0.0064$35.75195.3M360k8h 28m5551
72GLM-5.30.0054$111.06362.5M755k19h 29m89310
73Gemini 3.7 Flash0.0054$6.5251.3M224k2h 40m2742
74GLM-5.30.0038$97.66297.0M573k19h 4m6335
75DeepSeek V4 Flash Vision Exp0.0028$12.40756.6M1.2M19h 8m175639
76DeepSeek V4 Flash Vision Exp0.0027$6.77415.2M638k18h 28m8377
77Gemini 3.7 Flash0.0020$17.05105.9M300k5h 32m3811
78Qwen3.8-Max0.0018$183.02558.1M1.7M19h 56m13751
79Qwen3.8-Max0.0016$153.43448.8M1.7M19h 59m12021
80GLM-5.3 Flash0.0015$14.67306.8M449k20h 1m7461
81Qwen3.8-Max0.0010$149.46419.0M1.2M19h 25m9932
82GLM-5.3 Flash0.0010$16.55339.1M548k17h 44m7405
83Gemini 3.7 Flash0.0009$11.2877.4M230k5h 1m3693
84Gemini 3.8 Flash0.0007$23.00212.3M376k5h 7m5263
85GLM-5.30.0006$94.18300.9M621k18h 57m59210
86GLM-5.3 Flash0.0002$12.16275.0M487k19h 36m6283
87GLM-5.3 Flash0.0001$17.12399.9M616k15h 49m8285
88Qwen3.8-Max0.0001$169.64519.3M1.6M20h 0m12391
89Muse Spark 1.20.0000$7.7740.8M287k2h 9m1825
90Inkling0.0000$6.727.0M25k22m1382
91Qwen3.8-Max0.0000$189.91559.5M1.9M19h 51m14643
92Kimi K30.0000$182.81498.0M1.4M20h 1m10632
93Muse Spark 1.20.0000$8.0738.9M412k3h 7m2024
94DeepSeek V4 Flash Vision Exp0.0000$11.01666.7M1.1M19h 11m146711
95Qwen3.8-Max-09020.0000$58.14147.3M957k20h 6m4341
96Qwen3.8-Max-09020.0000$33.94103.0M952k20h 7m3671
97Muse Spark 1.20.0000$6.3024.2M135k1h 37m1594
98Qwen3.8-Max-09020.0000$41.8596.9M886k20h 4m4141
99Claude Fable 50.0000$411.65293.0M731k19h 45m6983
100GLM-5.30.0000$103.09375.1M554k19h 46m79012
101Gemini 3.8 Flash0.0000$53.67394.0M628k13h 26m10684
102Inkling0.0000$6.596.8M31k2h 10m1462
103Muse Spark 1.20.0000†$2.6412.4M42k2h 25m902
104Qwen3.8-Max-09020.0000$50.29127.1M914k20h 7m4791
105Inkling0.0000$6.576.8M31k35m1561
106GLM-5.3 Flash0.0000$17.57389.3M753k20h 0m8918
107Qwen3.8-Max-09020.0000$56.38146.6M1.2M20h 0m4681
108Inkling0.0000$4.244.4M17k41m1091
109Inkling0.0000$8.879.2M43k1h 49m1702
110Muse Spark 1.20.0000†$1.728.1M39k1h 17m881

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

FrogsGame Post-Training

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.9920$41.94172.9M571k18h 38m3581
2Claude Sonnet 5.50.9920$37.06145.6M621k18h 34m2894
3Claude Sonnet 5.50.9860$40.55166.2M572k19h 5m3631
4Claude Fable 5.10.9740$14.4121.9M144k17h 0m1535
5GPT-6 Astra0.9700$116.6760.2M205k18h 38m2558
6Claude Opus 5.50.9380$18.1054.0M277k17h 56m2033
7Claude Sonnet 5.50.9380$31.79125.6M517k19h 26m2942
8Claude Opus 5.50.9340$25.6782.0M341k18h 34m2486
9Claude Opus 5.50.9320$21.1864.6M311k18h 52m2285
10GPT-6 Astra0.9160$256.74124.3M279k19h 10m36511
11Claude Sonnet 5.50.9160$33.87130.0M616k16h 46m2793
12Claude Opus 5.50.9060$27.7293.7M337k17h 43m2924
13GPT-6 Astra0.9000$49.9727.6M160k19h 17m1586
14Gemini 4 Argon0.8920$46.0449.7M235k14h 34m1725
15Claude Fable 5.10.8920$12.7119.5M122k16h 12m1464
16Claude Haiku 5.50.8900$4.9880.9M361k18h 50m2475
17GPT-6 Astra0.8840$265.88128.3M310k19h 14m3908
18Claude Haiku 5.50.8580$5.6592.0M404k18h 43m2721
19Claude Haiku 5.50.8540$5.0178.6M413k17h 14m2351
20GLM-5.30.8380$21.9547.4M206k19h 31m2332
21Claude Opus 5.50.8240$28.1995.1M341k18h 8m2965
22Gemini 4 Argon0.8020$82.9162.7M281k14h 57m1664
23Claude Fable 5.10.7800$16.4025.5M151k15h 15m1653
24Claude Fable 50.7400$44.2130.2M189k19h 22m1914
25GLM-5.30.7220$12.9144.6M176k19h 17m2472
26Claude Opus 50.7140$29.7741.4M245k19h 28m2072
27Gemini 4 Argon0.6900$75.1061.9M250k17h 44m1914
28Claude Opus 50.6840$35.5851.9M259k19h 2m2252
29GPT-6 Astra0.6760$444.71214.4M392k19h 40m52110
30Claude Opus 50.6660$32.3644.1M277k18h 32m1924
31Claude Fable 5.10.6180$15.2423.4M145k17h 43m1626
32Muse Spark 1.30.6080$42.7636.7M222k19h 41m2412
33Gemini 4 Argon0.6040$30.5635.0M214k7h 42m1483
34Gemini 4 Argon0.5940$87.6965.7M221k8h 37m1753
35Claude Fable 50.5920$48.4932.7M211k19h 14m1773
36Claude Haiku 5.50.5500$7.58127.1M460k19h 19m3376
37Claude Opus 50.5280$40.0456.7M315k17h 56m2224
38Claude Haiku 5.50.5220$5.6892.2M413k18h 50m2842
39Grok 4.70.4940$60.7936.4M219k19h 41m1691
40Kimi K30.4620$12.7324.9M159k19h 34m1721
41Claude Fable 5.10.4080$13.0419.3M141k15h 46m1354
42Grok 4.70.3640$259.38236.3M353k19h 57m7952
43GLM-5.30.3120$16.4057.5M195k19h 21m3142
44Kimi K30.3000$16.0038.1M240k20h 0m1871
45Grok 4.70.2980$90.9963.2M209k18h 43m2772
46Claude Fable 50.2940$55.2838.9M218k19h 5m1964
47Grok 4.70.2920$118.9466.1M194k19h 26m2822
48Claude Opus 50.2740$33.2345.6M283k19h 1m2002
49Claude Fable 50.2640$49.5234.1M206k18h 52m1864
50Grok 4.60.2460$18.5719.8M283k19h 59m1521
51Grok 4.60.2420$9.6812.9M262k19h 22m1322
52Qwen3.8-Max0.2160$11.9738.7M277k19h 34m2973
53Kimi K30.1900$13.6332.0M177k20h 0m1981
54GLM-5.30.1640$20.8241.0M222k19h 4m2143
55GLM-5.30.1580$16.5958.5M233k19h 38m2651
56Claude Fable 50.1360$52.2635.5M227k18h 52m1834
57Muse Spark 1.30.1340$12.4916.7M201k19h 20m1793
58Grok 4.60.1280$47.6745.1M287k18h 35m2595
59DeepSeek V4 Flash Vision Exp0.1100$1.2765.0M240k20h 4m3061
60GLM-5.3 Flash0.1040$2.4843.2M239k18h 52m2062
61Kimi K30.1040$11.1320.9M147k19h 47m1741
62GLM-5.3 Flash0.1020$2.4858.2M263k18h 49m2672
63Qwen3.8-Max0.0980$10.6932.2M339k19h 46m2721
64Gemini 3.8 Flash0.0960$23.82139.9M200k8h 48m45031
65Gemini 3.8 Flash0.0900$36.72152.5M162k13h 5m4203
66GPT-5.6 Sol0.0900$19.4628.7M100k17h 8m2062
67Qwen3.8-Max0.0880$5.8516.5M229k19h 7m1951
68DeepSeek V4 Flash Vision Exp0.0860$1.4779.6M227k19h 17m3902
69Qwen3.8-Max-09020.0680$32.05102.3M870k19h 37m4062
70Kimi K30.0660$8.1017.2M123k19h 18m1531
71Grok 4.60.0640$49.0243.5M397k19h 5m2214
72Gemini 3.7 Flash0.0620$5.0314.3M76k5h 27m1281
73Muse Spark 1.30.0580$11.2613.8M164k19h 42m1633
74GPT-5.6 Sol0.0540$20.8732.1M115k12h 56m2413
75Grok 4.70.0460$50.6836.5M192k18h 50m1962
76GLM-5.3 Flash0.0420$2.0126.5M194k19h 34m1691
77Gemini 3.7 Flash0.0420$30.7272.9M130k16h 34m3011
78GPT-5.6 Sol0.0380$22.1134.6M103k18h 7m2232
79Muse Spark 1.30.0380$29.7531.6M256k19h 58m2611
80GPT-5.6 Sol0.0360$61.3164.5M145k15h 2m2772
81Qwen3.8-Max0.0360$35.74120.9M650k19h 55m5462
82Gemini 3.8 Flash0.0340$11.7559.4M141k7h 14m2764
83Grok 4.60.0340$48.2946.2M363k16h 43m2375
84Qwen3.8-Max-09020.0320$32.58103.5M819k19h 35m4152
85Gemini 3.7 Flash0.0320$45.33138.6M173k19h 58m3961
86Muse Spark 1.30.0320$20.0329.7M151k19h 22m2411
87Gemini 3.8 Flash0.0300$54.93193.3M322k19h 11m5172
88Qwen3.8-Max0.0300$11.9837.6M292k18h 44m3234
89Muse Spark 1.20.0300$18.3645.0M166k4h 11m1765
90GLM-5.3 Flash0.0280$2.0252.4M227k19h 53m2711
91Gemini 3.8 Flash0.0240$6.6228.1M109k3h 35m1582
92Qwen3.8-Max-09020.0220$35.21102.2M1.1M19h 56m399—
93Qwen3.8-Max-09020.0220$33.10101.6M958k19h 40m4303
94Gemini 3.7 Flash0.0220$3.8024.6M101k2h 41m1422
95Muse Spark 1.20.0220$21.7448.9M286k5h 11m23911
96Gemini 3.7 Flash0.0200$37.0796.2M140k17h 26m3211
97GLM-5.3 Flash0.0160$3.0357.8M247k19h 17m2542
98DeepSeek V4 Flash Vision Exp0.0160$1.3368.9M247k19h 56m3452
99DeepSeek V4 Flash Vision Exp0.0160$1.1355.9M221k19h 37m2642
100GPT-5.6 Sol0.0120$91.1851.7M86k17h 41m2284
101Muse Spark 1.20.0100$18.40105.2M433k4h 43m2515
102Inkling0.0080$2.602.6M22k28m842
103Muse Spark 1.20.0060$13.7365.6M312k5h 25m1839
104Inkling0.0000$8.378.7M31k38m1692
105DeepSeek V4 Flash Vision Exp0.0000$1.6187.5M249k20h 2m3951
106Inkling0.0000$3.543.7M16k24m972
107Inkling0.0000$1.631.6M18k24m712
108Muse Spark 1.20.0000$196.241245.9M587k4h 6m23898
109Qwen3.8-Max-09020.0000$4.949.5M357k5h 14m931
110Inkling0.0000$2.522.6M17k28m1032

Git to Zig

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.9864$3111.971407.9M3.4M19h 58m311948
2GPT-6 Astra0.9049$3006.211380.7M3.3M20h 0m312960
3GPT-6 Astra0.8950$2950.791350.4M3.3M19h 50m303152
4GPT-6 Astra0.8938$3057.891408.3M3.3M19h 59m320496
5GPT-6 Astra0.8893$3214.361493.6M3.2M19h 59m334799
6Claude Opus 5.50.6812$313.471048.3M4.0M19h 32m243625
7Claude Opus 5.50.6644$241.59773.6M3.3M19h 40m184333
8Claude Opus 5.50.6378$222.91717.3M3.1M19h 51m160719
9Claude Opus 5.50.6246$242.07814.4M3.0M19h 50m177332
10Claude Sonnet 5.50.6193$286.711152.7M4.4M19h 47m266217
11Claude Sonnet 5.50.6146$288.131151.1M4.5M19h 38m248713
12Claude Sonnet 5.50.6064$328.101331.6M4.8M19h 55m30718
13Claude Opus 5.50.5824$188.65606.3M2.6M19h 43m143734
14Claude Fable 5.10.5599$663.301199.7M2.6M18h 57m267417
15Claude Sonnet 5.50.5548$219.87857.0M3.8M19h 46m203010
16Gemini 4 Argon0.5447$362.36783.2M2.2M20h 48m175326
17Claude Sonnet 5.50.5357$185.56725.4M3.2M19h 53m17638
18Gemini 4 Argon0.5225$190.93727.6M2.5M20h 51m165723
19Claude Fable 5.10.5146$566.081019.0M2.3M19h 11m236013
20Claude Fable 5.10.5049$432.88762.8M2.1M18h 58m173213
21Claude Fable 5.10.4886$363.29631.2M2.0M18h 58m156211
22Claude Fable 5.10.4844$390.64686.7M2.0M19h 13m161126
23Gemini 4 Argon0.4697$330.68663.7M1.9M20h 55m156911
24Gemini 4 Argon0.4294$398.78647.4M2.0M20h 52m148726
25Gemini 4 Argon0.4167$333.71642.4M2.0M20h 59m140231
26Claude Fable 50.4059$841.49687.0M2.0M19h 35m153422
27Claude Fable 50.4009$1051.04892.5M2.1M19h 47m194325
28Claude Opus 50.3856$635.161128.1M1.8M19h 53m241122
29Claude Fable 50.3814$1038.32878.7M2.1M19h 45m194222
30Claude Opus 50.3683$533.23935.7M1.7M19h 23m182615
31Claude Fable 50.3565$966.19820.9M1.9M19h 53m171014
32GPT-5.6 Sol0.3440$1238.081225.0M944k19h 8m262721
33Claude Opus 50.3411$614.971098.7M1.7M19h 37m220622
34Claude Fable 50.3411$903.80768.8M1.8M19h 40m167210
35Claude Haiku 5.50.3210$69.201225.1M2.9M18h 51m25643
36Claude Haiku 5.50.3209$63.681097.5M3.2M19h 26m234844
37Claude Opus 50.3150$429.99753.2M1.4M19h 44m166018
38Claude Opus 50.3034$490.76870.1M1.4M19h 44m197413
39Claude Haiku 5.50.2918$66.191196.6M2.4M17h 47m253917
40Claude Haiku 5.50.2897$71.591281.2M2.8M19h 16m275324
41Claude Haiku 5.50.2814$60.901077.6M2.7M19h 17m225120
42GPT-5.6 Sol0.2804$1082.721080.1M850k19h 36m231442
43GPT-5.6 Sol0.2801$1175.971171.4M884k19h 37m260229
44Grok 4.70.2530$1242.681266.7M4.0M20h 0m506870
45Grok 4.70.2469$910.55936.9M2.7M19h 58m376853
46GPT-5.6 Sol0.2369$955.56945.7M722k19h 4m198213
47Grok 4.70.2342$1107.041144.5M3.0M20h 0m463866
48Grok 4.70.2156$741.65767.0M2.0M19h 54m309973
49Gemini 3.8 Flash0.1938$193.402143.9M2.9M19h 15m475123
50Grok 4.70.1876$623.38637.1M2.0M13h 32m260018
51GPT-5.6 Sol0.1874$770.31763.5M629k19h 0m16686
52Gemini 3.7 Flash0.1808$157.011517.8M2.4M19h 43m32561
53Gemini 3.8 Flash0.1795$179.041977.0M2.7M19h 44m429317
54Kimi K30.1768$251.00752.4M1.2M20h 2m16191
55Kimi K30.1733$200.20602.7M965k19h 43m148313
56Gemini 3.8 Flash0.1706$167.161718.1M2.3M19h 49m393219
57Grok 4.60.1693$652.70657.8M2.2M19h 59m2502122
58Gemini 3.8 Flash0.1621$197.442159.7M2.7M19h 47m487228
59Grok 4.60.1618$614.44610.4M2.6M18h 0m232473
60Kimi K30.1616$254.18761.8M1.1M19h 47m16689
61Gemini 3.8 Flash0.1604$196.692138.2M2.7M20h 0m469426
62Kimi K30.1574$259.84779.9M1.1M19h 53m17652
63GLM-5.30.1556$225.36842.0M964k19h 45m201217
64GLM-5.30.1531$195.54692.6M689k19h 54m14802
65Grok 4.60.1516$806.68819.7M2.2M19h 59m2981186
66Inkling0.1510$17.7718.6M32k1h 29m2551
67Gemini 3.7 Flash0.1495$79.59838.0M1.2M20h 0m18552
68Kimi K30.1473$222.64660.4M1.1M19h 44m14911
69Gemini 3.7 Flash0.1433$101.571069.8M1.5M19h 58m23721
70GLM-5.3 Flash0.1431$24.60751.1M974k19h 4m175213
71Muse Spark 1.30.1427$402.31656.1M1.1M18h 56m16323
72GLM-5.30.1390$212.77708.2M852k19h 49m164049
73GLM-5.30.1378$248.79932.5M906k19h 55m221921
74Grok 4.60.1352$482.88483.0M1.6M11h 22m176784
75GLM-5.3 Flash0.1328$26.79827.0M1.1M19h 10m175110
76GLM-5.3 Flash0.1304$29.71954.5M1.0M19h 55m203510
77DeepSeek V4 Flash Vision Exp0.1304$28.181759.3M2.2M19h 24m372315
78Muse Spark 1.30.1274$518.45593.9M920k19h 54m14652
79Grok 4.60.1269$408.61405.7M1.8M19h 55m155848
80GLM-5.3 Flash0.1260$27.25852.3M924k19h 18m18736
81Gemini 3.7 Flash0.1237$71.55746.3M1.3M19h 57m16904
82GLM-5.30.1219$188.86712.0M621k19h 43m131816
83DeepSeek V4 Flash Vision Exp0.1213$28.061756.1M2.2M19h 43m379311
84Qwen3.8-Max0.1212$184.24696.5M1.3M19h 33m180512
85GLM-5.3 Flash0.1195$28.09863.8M1.0M19h 28m200013
86DeepSeek V4 Flash Vision Exp0.1193$26.161630.6M2.1M19h 37m35848
87Qwen3.8-Max-09020.1143$142.85503.3M2.3M19h 27m13358
88DeepSeek V4 Flash Vision Exp0.1079$21.831364.0M1.7M17h 17m29778
89Muse Spark 1.30.1062$484.87561.8M975k20h 0m14991
90Qwen3.8-Max0.1038$196.74742.9M1.4M19h 38m183126
91Qwen3.8-Max0.1023$180.44685.7M1.2M19h 14m17762
92Muse Spark 1.30.1006$482.98557.2M1.0M20h 0m159415
93DeepSeek V4 Flash Vision Exp0.0988$20.501272.8M1.7M19h 17m273211
94Qwen3.8-Max0.0987$178.20662.0M1.7M19h 50m17106
95Qwen3.8-Max0.0927$190.64725.2M1.3M19h 52m162035
96Qwen3.8-Max-09020.0891$199.99712.3M3.1M19h 47m16659
97Qwen3.8-Max-09020.0536$90.79292.3M2.5M20h 1m7882
98Qwen3.8-Max-09020.0529$127.39412.8M3.6M20h 1m11581
99Muse Spark 1.20.0185$42.33250.7M911k3h 1m5785
100Inkling0.0093$17.5218.3M28k1h 29m2083
101Qwen3.8-Max-09020.0086$101.78346.1M2.1M20h 0m9162
102Inkling0.0019$16.3617.1M30k17m2801
103Muse Spark 1.20.0000†$2.459.3M123k59m862
104Inkling0.0000$3.153.3M13k5m862
105Muse Spark 1.30.0000$641.52782.0M1.4M19h 59m15801
106Muse Spark 1.20.0000†$5.5326.0M135k1h 56m1754
107Muse Spark 1.20.0000†$59.99358.3M658k4h 22m7791
108Gemini 3.7 Flash0.0000†$76.41819.6M1.5M19h 43m17341
109Inkling0.0000†$5.575.8M17k1h 55m1182
110Muse Spark 1.20.0000†$2.147.7M83k1h 10m933

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Granite Mamba2 Inference Optimization

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.9284$98.15363.7M2.0M12h 14m7582
2Gemini 4 Argon0.9104$105.47115.9M895k5h 40m3156
3Qwen3.8-Max-09020.9095$72.15209.6M2.3M19h 47m5632
4Gemini 4 Argon0.9046$83.33130.1M792k5h 37m3593
5Gemini 4 Argon0.8993$145.24118.2M769k6h 54m3318
6GLM-5.30.8927$85.79297.0M636k6h 7m6347
7Claude Haiku 5.50.8911$15.33230.6M1.3M10h 52m5002
8Gemini 4 Argon0.8884$91.0370.1M500k3h 12m1953
9Claude Opus 5.50.8846$214.03690.9M2.9M15h 36m150634
10Gemini 4 Argon0.8832$36.1898.9M556k3h 28m2363
11Claude Opus 5.50.8817$132.91426.3M1.8M6h 35m92225
12Claude Opus 5.50.8769$159.17476.8M2.5M11h 3m109429
13GLM-5.30.8719$51.39174.8M618k4h 8m3828
14DeepSeek V4 Flash Vision Exp0.8708$2.68149.8M376k16h 23m4735
15GPT-6 Astra0.8707$2626.811259.5M2.3M18h 25m283958
16GPT-6 Astra0.8658$272.49128.6M369k2h 40m3677
17Claude Sonnet 5.50.8655$166.81620.5M3.4M17h 36m134614
18Claude Opus 50.8619$158.22232.0M1.1M7h 45m54310
19Grok 4.70.8555$664.66670.3M2.4M20h 0m251555
20Claude Fable 5.10.8458$138.31228.0M1000k9h 1m58015
21GLM-5.30.8401$45.93158.7M655k5h 28m3436
22Claude Opus 50.8400$159.98236.7M1.1M11h 10m56615
23Claude Fable 5.10.8393$189.96320.0M1.2M8h 30m71828
24Claude Haiku 5.50.8379$8.93123.1M1.0M4h 22m3013
25Claude Fable 50.8372$204.33157.4M642k12h 58m31020
26GPT-6 Astra0.8334$251.26124.6M331k2h 35m4094
27Claude Haiku 5.50.8309$11.48157.4M1.3M4h 35m3864
28Grok 4.70.8303$663.28652.6M2.1M14h 34m234524
29GPT-6 Astra0.8266$344.95163.8M406k3h 8m4598
30GPT-6 Astra0.8198$254.82122.3M354k2h 28m3747
31Claude Fable 5.10.8171$168.52281.0M1.2M8h 8m66716
32Muse Spark 1.20.8168$5.1625.8M238k1h 23m1693
33Qwen3.8-Max-09020.8140$43.2091.8M3.2M19h 47m3541
34Muse Spark 1.30.8136$31.6238.2M374k3h 49m1865
35Qwen3.8-Max0.8086$63.86200.9M2.1M18h 31m5722
36Claude Fable 5.10.8047$204.26349.5M1.2M8h 27m78431
37Muse Spark 1.30.8036$155.17181.2M487k18h 42m54511
38Claude Haiku 5.50.8023$12.99188.9M1.3M8h 53m4512
39GLM-5.3 Flash0.7990$11.45322.1M969k12h 30m7914
40Qwen3.8-Max-09020.7969$68.75217.9M2.1M19h 23m5952
41Inkling0.7968$5.415.6M24k1h 10m983
42Claude Fable 50.7947$155.09112.6M581k5h 11m2479
43Inkling0.7910$2.642.7M12k47m612
44DeepSeek V4 Flash Vision Exp0.7876$3.53195.8M540k19h 32m5198
45Qwen3.8-Max0.7876$54.77177.9M1.6M16h 1m5205
46Kimi K30.7872$122.78337.3M986k19h 10m77136
47Claude Fable 5.10.7867$157.78258.9M1.2M7h 40m58211
48GLM-5.3 Flash0.7842$10.09304.8M714k7h 37m5958
49Gemini 3.7 Flash0.7839$8.9784.4M442k56m2813
50Muse Spark 1.30.7809$183.67203.2M648k10h 29m55711
51Kimi K30.7805$103.11286.2M907k14h 49m65110
52Grok 4.70.7778$748.71746.1M3.0M20h 0m276323
53Claude Opus 50.7718$80.48113.3M644k3h 51m2435
54Inkling0.7670$5.685.8M36k1h 22m1012
55GPT-5.6 Sol0.7649$74.7474.2M207k2h 36m2705
56DeepSeek V4 Flash Vision Exp0.7578$8.78501.2M1.2M13h 5m11573
57Kimi K30.7571$91.87248.8M620k20h 0m53150
58GLM-5.30.7528$38.94126.7M486k4h 14m3515
59Claude Opus 5.50.7510$78.62226.6M1.3M6h 44m47812
60Kimi K30.7477$74.48205.5M639k8h 3m45620
61Grok 4.70.7473$45.1945.2M263k1h 21m1813
62DeepSeek V4 Flash Vision Exp0.7467$8.27472.9M1.1M11h 58m114023
63GLM-5.3 Flash0.7460$13.06377.4M1.1M12h 40m9702
64Claude Haiku 5.50.7446$23.17349.9M2.1M10h 30m7634
65GLM-5.3 Flash0.7421$9.37261.1M646k9h 26m5352
66GLM-5.30.7402$85.05310.6M673k18h 16m6458
67Claude Fable 50.7331$198.58154.1M599k9h 40m30216
68Grok 4.60.7305$58.7452.8M626k4h 20m20613
69Grok 4.60.7245$46.6739.7M692k3h 57m16910
70Qwen3.8-Max0.7188$63.39207.4M1.7M17h 14m5579
71Muse Spark 1.20.7107$36.53207.7M800k2h 20m5271
72Qwen3.8-Max0.7023$29.6470.4M1.9M19h 40m3301
73Claude Opus 50.6979$228.77352.0M1.4M11h 8m75118
74Claude Sonnet 5.50.6871$127.04479.4M2.5M17h 41m106310
75Qwen3.8-Max0.6658$53.16162.1M1.8M18h 29m4952
76Grok 4.60.6586$55.7047.5M700k4h 6m19410
77Grok 4.60.6473$57.8851.1M725k4h 13m2105
78Muse Spark 1.30.6457$320.20329.1M590k13h 47m77312
79GPT-5.6 Sol0.6303$111.93116.6M261k11h 2m4253
80Muse Spark 1.30.6302$29.9288.8M460k3h 13m3259
81Kimi K30.6169$112.73307.9M980k13h 16m70831
82Qwen3.8-Max-09020.6109$38.4677.0M3.0M18h 44m2982
83GPT-5.6 Sol0.6093$23.5332.7M162k1h 28m2073
84Claude Fable 50.5974$289.56218.1M971k11h 20m52929
85Claude Opus 5.50.5826$111.15316.0M1.9M10h 19m73129
86Claude Sonnet 5.50.5555$156.83594.5M3.0M18h 16m12754
87Claude Fable 50.5364$304.87227.0M1.1M13h 5m53222
88Claude Opus 50.5059$98.60149.0M645k5h 53m2877
89Gemini 3.8 Flash0.5042$12.98108.1M394k2h 18m3295
90Claude Sonnet 5.50.4810$155.71584.6M3.1M16h 20m12908
91DeepSeek V4 Flash Vision Exp0.4680$3.00159.1M520k6h 30m4425
92GPT-5.6 Sol0.4658$119.15122.5M308k3h 17m4636
93GLM-5.3 Flash0.4647$8.11210.3M541k9h 13m4733
94Grok 4.70.4410$49.6548.3M283k2h 1m18413
95Gemini 3.8 Flash0.4012$12.80133.1M348k1h 19m3602
96Gemini 3.7 Flash0.3912$15.89144.8M798k2h 17m4795
97Gemini 3.8 Flash0.3668$11.65115.4M351k1h 8m3536
98GPT-5.6 Sol0.3383$180.46175.3M266k4h 7m47410
99Gemini 3.7 Flash0.3149$10.7497.9M514k1h 12m2782
100Gemini 3.8 Flash0.2792$7.7171.8M268k1h 9m2832
101Grok 4.60.2777$27.6423.0M551k3h 18m1272
102Gemini 3.7 Flash0.2425$12.51121.4M559k2h 10m3262
103Gemini 3.7 Flash0.2101$6.7049.8M379k47m2123
104Inkling0.0000$7.507.7M51k1h 46m1351
105Gemini 3.8 Flash0.0000$15.57160.4M440k1h 35m4091
106Qwen3.8-Max-09020.0000$60.04188.3M1.9M19h 52m4973
107Muse Spark 1.20.0000$19.4092.0M1.0M4h 3m3073
108Muse Spark 1.20.0000$9.9353.1M354k2h 11m2586
109Muse Spark 1.20.0000$8.0539.0M223k1h 17m2014
110Inkling0.0000$4.664.8M18k1h 13m912

Higgs Uncertainty Inference

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra1.0000$164.9780.6M296k2h 47m3068
2Claude Opus 51.0000$43.0055.4M421k5h 4m1934
3Claude Opus 5.51.0000$25.5770.3M442k6h 17m21111
4Claude Opus 51.0000$43.7358.4M394k12h 22m2106
5GPT-6 Astra1.0000$50.7531.1M211k1h 50m1846
6Claude Fable 5.10.9930$40.5965.5M322k8h 40m2419
7Claude Opus 5.50.9897$30.0390.4M459k7h 8m25813
8Claude Sonnet 5.50.9897$29.45110.7M573k6h 41m2594
9Claude Fable 5.10.9895$33.5652.1M309k8h 2m2218
10Qwen3.8-Max0.9778$23.7479.2M556k12h 13m42814
11GPT-6 Astra0.9768$52.9333.2M214k1h 55m2005
12DeepSeek V4 Flash Vision Exp0.9597$1.5170.8M347k3h 23m2834
13Claude Sonnet 5.50.9593$30.61116.2M578k14h 56m2752
14Kimi K30.9593$29.5562.1M341k12h 49m28515
15Claude Fable 50.9397$59.1436.3M315k5h 54m1628
16Claude Fable 50.9375$84.7058.1M370k13h 38m22814
17Claude Opus 5.50.9370$28.5384.2M453k7h 52m26012
18Qwen3.8-Max-09020.9183$45.24139.4M1.5M19h 44m4281
19Grok 4.60.9143$37.2334.8M407k3h 22m15810
20Muse Spark 1.20.9041$8.8738.4M436k2h 57m1501
21Grok 4.60.8991$42.7739.2M529k3h 38m1839
22Claude Sonnet 5.50.8984$37.57147.8M629k11h 9m3144
23Claude Haiku 5.50.8970$5.8485.5M559k11h 56m2222
24Grok 4.60.8827$39.9237.7M462k3h 38m1818
25Inkling0.8760$6.246.3M65k37m1401
26Claude Haiku 5.50.8579$4.6565.6M502k5h 43m1882
27Muse Spark 1.30.8206$37.7359.2M320k3h 38m30012
28Grok 4.60.8188$274.70264.2M1.9M19h 38m107867
29GPT-5.6 Sol0.7863$99.9097.4M228k4h 26m32720
30Grok 4.70.7706$11.9313.0M204k1h 11m905
31Qwen3.8-Max0.7685$16.6651.1M571k13h 28m3425
32Muse Spark 1.30.7474$18.6743.3M220k4h 23m2506
33DeepSeek V4 Flash Vision Exp0.7308$2.17110.7M423k3h 32m3749
34Muse Spark 1.20.7187$4.4015.5M216k1h 29m1102
35Muse Spark 1.20.7132$3.9618.1M225k49m1264
36Qwen3.8-Max-09020.5260$31.3194.3M1.1M19h 31m3411
37Claude Sonnet 5.50.4600$33.95128.3M649k6h 32m2723
38Gemini 3.8 Flash0.4507$3.6326.5M187k49m1773
39Claude Opus 50.4324$63.2091.3M476k9h 29m26711
40GPT-6 Astra0.4310$132.0368.3M275k2h 40m2895
41Qwen3.8-Max0.4289$16.2149.4M555k8h 58m2858
42Kimi K30.4200$32.1858.0M281k15h 50m2808
43Claude Opus 50.3824$73.86111.1M500k10h 52m31611
44Muse Spark 1.30.3726$625.66665.8M679k19h 55m1128223
45Muse Spark 1.30.3641$40.7252.7M332k3h 49m2578
46Qwen3.8-Max0.3449$15.6147.3M543k7h 37m2788
47Gemini 4 Argon0.3435$96.8559.0M525k6h 34m1552
48Qwen3.8-Max-09020.3378$32.6597.4M1.2M19h 38m3761
49Claude Fable 5.10.3345$30.4545.8M311k4h 14m17415
50Gemini 3.8 Flash0.3266$3.8926.2M153k53m1773
51Gemini 4 Argon0.3199$35.6242.7M359k5h 46m1553
52Qwen3.8-Max0.3078$18.5657.9M578k8h 28m3226
53Claude Opus 50.3011$69.90100.7M538k8h 25m2685
54Claude Opus 5.50.2834$29.0888.4M439k9h 41m26510
55Claude Opus 5.50.2805$36.69117.7M504k7h 47m31012
56Claude Sonnet 5.50.2521$37.68144.7M683k9h 35m2973
57Claude Fable 50.2381$63.3541.3M309k8h 51m19711
58Gemini 4 Argon0.2379$42.74116.3M781k7h 14m2814
59Claude Fable 50.2345$86.5863.1M319k16h 11m2647
60Gemini 3.8 Flash0.2264$4.4236.8M191k1h 14m2025
61Claude Haiku 5.50.2175$5.4175.1M593k4h 10m2032
62Gemini 4 Argon0.2135$100.4483.2M842k7h 14m2394
63Grok 4.60.2104$116.88112.5M824k9h 43m47052
64GPT-5.6 Sol0.2084$52.2656.6M152k2h 42m2445
65GPT-6 Astra0.2020$84.8443.9M239k1h 53m2086
66Claude Fable 5.10.2017$30.5147.2M284k6h 48m1949
67Qwen3.8-Max-09020.1773$37.51112.2M1.0M19h 48m4616
68Gemini 3.7 Flash0.1681$1.729.3M135k1h 3m1021
69Claude Fable 50.1639$81.1355.6M354k15h 53m22411
70GLM-5.30.1632$24.1184.1M350k8h 48m3108
71Muse Spark 1.20.1494$13.1065.0M597k2h 52m2671
72Claude Haiku 5.50.1334$4.5663.7M502k4h 40m1872
73Gemini 3.7 Flash0.1295$1.9810.2M141k50m1053
74Gemini 4 Argon0.1190$36.0353.9M536k3h 17m1623
75Gemini 3.7 Flash0.1075$1.629.2M146k1h 7m1021
76Claude Haiku 5.50.1032$5.8883.3M608k3h 20m2161
77GLM-5.30.1005$24.4671.1M367k17h 31m2837
78Kimi K30.0960$32.3577.4M380k13h 56m31115
79Qwen3.8-Max-09020.0834$33.1298.6M1.2M19h 40m3711
80Gemini 3.7 Flash0.0798$2.5310.3M161k1h 26m1101
81Claude Fable 5.10.0778$29.8844.4M316k2h 48m18313
82GPT-5.6 Sol0.0777$44.3350.5M161k1h 56m2296
83DeepSeek V4 Flash Vision Exp0.0718$2.02102.8M397k15h 29m3464
84DeepSeek V4 Flash Vision Exp0.0700$1.5070.3M352k6h 13m2906
85Gemini 3.7 Flash0.0647$3.7920.7M194k1h 41m1392
86Kimi K30.0626$34.0868.6M372k14h 20m27512
87DeepSeek V4 Flash Vision Exp0.0559$1.3262.9M305k6h 32m2784
88GLM-5.30.0517$9.9130.6M263k2h 10m1675
89Muse Spark 1.20.0498$2.478.0M164k1h 0m832
90GLM-5.30.0375$14.9449.5M308k3h 28m2232
91Gemini 3.8 Flash0.0340$3.0420.0M136k40m1644
92Muse Spark 1.30.0300$39.3251.4M265k3h 54m2618
93Kimi K30.0289$90.08230.0M659k20h 0m5551
94GLM-5.30.0251$17.6860.0M356k3h 29m2463
95GPT-5.6 Sol0.0080$56.4460.4M164k6h 2m25912
96Inkling0.0078$3.623.6M51k2h 38m1201
97Gemini 3.8 Flash0.0073$2.1314.4M132k40m1362
98GPT-5.6 Sol0.0049$70.6365.2M124k2h 29m1946
99Inkling0.0004$3.373.3M54k1h 37m1041
100Inkling0.0004$4.084.1M54k1h 12m1122
101Grok 4.70.0000$420.44408.4M739k19h 20m129318
102Grok 4.70.0000$7.848.3M179k58m633
103Inkling0.0000$2.472.5M36k1h 12m1061
104GLM-5.3 Flash0.0000$3.3653.3M330k10h 44m2306
105GLM-5.3 Flash0.0000$3.5784.9M393k10h 21m2842
106Grok 4.70.0000$17.2117.6M220k1h 13m995
107GLM-5.3 Flash0.0000$2.0535.6M271k7h 4m2023
108Grok 4.70.0000$9.2910.1M177k1h 2m762
109GLM-5.3 Flash0.0000$1.7038.2M299k3h 32m1834
110GLM-5.3 Flash0.0000$4.9095.4M391k15h 5m3127

Kolmogorov Audio Compression

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra1.0000$2526.291186.0M2.6M19h 52m274860
2GPT-6 Astra1.0000$2608.331211.7M2.6M19h 14m257757
3GPT-6 Astra1.0000$2728.801295.7M2.6M19h 47m292059
4GPT-6 Astra1.0000$1955.97919.3M1.8M13h 34m203127
5Gemini 4 Argon0.1051$267.43253.9M1.3M20h 43m65014
6Claude Sonnet 5.50.0978$108.60441.2M1.6M19h 39m105110
7Claude Sonnet 5.50.0941$68.80277.4M1.1M19h 3m6951
8Claude Sonnet 5.50.0934$70.90283.8M1.1M19h 20m68913
9Claude Sonnet 5.50.0867$89.81366.1M1.3M19h 24m77915
10Claude Opus 5.50.0856$64.20240.0M620k16h 10m53020
11Claude Sonnet 5.50.0850$134.99552.5M1.9M17h 54m11746
12Claude Opus 5.50.0830$83.18303.7M858k18h 27m75919
13Claude Opus 5.50.0789$67.50264.9M554k16h 28m61417
14Gemini 4 Argon0.0786$189.34268.5M1.6M19h 23m66114
15Claude Opus 5.50.0783$41.46140.9M515k18h 1m39617
16Claude Fable 5.10.0779$45.1977.6M262k17h 49m33416
17Gemini 4 Argon0.0759$254.33211.1M1.1M19h 34m46611
18Claude Fable 5.10.0754$52.3588.6M331k12h 35m33910
19Claude Fable 5.10.0711$71.87125.0M385k17h 43m41418
20Claude Opus 50.0709$49.7973.0M367k18h 21m2879
21Claude Opus 50.0708$49.8272.2M372k18h 28m2586
22Claude Opus 50.0704$79.01124.4M464k18h 51m36613
23GPT-6 Astra0.0696$683.33329.9M756k19h 26m87916
24Claude Fable 5.10.0695$54.4693.0M327k16h 46m34711
25Claude Opus 5.50.0694$57.79216.0M560k18h 11m50014
26Claude Fable 50.0684$67.9348.0M274k18h 50m2567
27Claude Fable 5.10.0678$47.9881.1M304k16h 17m33310
28Claude Haiku 5.50.0650$9.87161.3M651k11h 38m3671
29Gemini 4 Argon0.0648$246.66202.6M896k20h 43m50810
30Claude Opus 50.0619$46.8066.5M370k18h 0m2509
31Claude Fable 50.0592$121.0693.1M386k19h 25m34015
32Claude Haiku 5.50.0578$7.35119.4M510k11h 49m3139
33Claude Haiku 5.50.0569$7.56123.0M501k18h 46m3294
34Claude Haiku 5.50.0566$12.02190.2M959k14h 47m4865
35Claude Fable 50.0559$85.5462.1M330k17h 58m27711
36Gemini 4 Argon0.0474$174.59205.7M1.1M13h 22m47218
37Grok 4.70.0462$180.50154.3M515k19h 45m6315
38Claude Fable 50.0444$66.8447.5M265k18h 38m2345
39GPT-5.6 Sol0.0416$183.22165.9M262k15h 47m47112
40Claude Haiku 5.50.0415$8.31137.0M537k14h 59m3622
41GPT-5.6 Sol0.0408$43.3247.2M136k19h 34m24910
42Claude Fable 50.0392$102.9478.4M342k18h 53m31719
43GLM-5.30.0369$28.7191.1M330k19h 38m3432
44GLM-5.30.0349$48.94118.7M352k19h 6m3842
45Grok 4.70.0329$52.4742.4M229k5h 56m21012
46GLM-5.3 Flash0.0316$3.9073.7M369k19h 44m2997
47Grok 4.70.0313$93.7878.9M256k12h 4m31314
48Kimi K30.0313$38.45102.2M362k20h 1m39710
49GLM-5.3 Flash0.0303$10.53223.0M596k19h 20m50215
50GLM-5.30.0298$35.1891.1M311k19h 41m36613
51GLM-5.3 Flash0.0288$2.9683.8M329k18h 56m3652
52GLM-5.3 Flash0.0270$4.3096.9M346k19h 28m3483
53DeepSeek V4 Flash Vision Exp0.0268$2.15112.2M397k7h 43m3893
54Kimi K30.0266$26.1560.2M321k19h 29m30313
55GLM-5.30.0264$29.0175.1M335k17h 41m3116
56Kimi K30.0251$50.26120.4M460k19h 45m4107
57Kimi K30.0250$34.5393.2M354k19h 44m3958
58Muse Spark 1.30.0247$73.5580.1M351k10h 48m3927
59GLM-5.30.0243$29.3996.9M323k19h 43m3561
60Gemini 3.7 Flash0.0240$13.44120.0M296k7h 42m4657
61Gemini 3.7 Flash0.0232$21.26112.5M588k9h 45m34020
62DeepSeek V4 Flash Vision Exp0.0228$5.13304.7M583k13h 30m7127
63GPT-5.6 Sol0.0224$49.4277.2M169k19h 53m42211
64Grok 4.60.0221$127.10131.5M617k19h 58m61730
65Grok 4.70.0218$33.8132.7M228k2h 52m1718
66Muse Spark 1.30.0215$70.2670.8M222k11h 3m36612
67Muse Spark 1.30.0200$64.2165.3M198k19h 54m4045
68Grok 4.60.0192$168.00174.0M498k19h 58m76868
69Muse Spark 1.30.0192$39.49134.3M306k19h 56m5683
70Gemini 3.7 Flash0.0189$26.8583.8M686k9h 43m26716
71Qwen3.8-Max-09020.0172$73.87221.2M2.8M19h 53m5702
72Grok 4.60.0171$114.81118.3M558k19h 40m59947
73Qwen3.8-Max0.0171$21.5569.7M606k19h 26m44615
74GPT-5.6 Sol0.0163$47.5455.3M185k19h 43m29110
75GPT-5.6 Sol0.0159$41.6061.4M164k18h 50m36811
76Qwen3.8-Max0.0155$18.8060.7M524k19h 36m4004
77Gemini 3.8 Flash0.0140$7.3446.3M196k3h 13m2746
78Qwen3.8-Max-09020.0136$47.03132.4M2.1M19h 23m4322
79Grok 4.70.0128$49.7744.3M205k7h 40m2316
80Muse Spark 1.20.0126$49.13229.2M341k8h 52m5756
81Grok 4.60.0126$162.44156.4M577k19h 37m63461
82Muse Spark 1.30.0124$64.7658.2M224k18h 13m38411
83Kimi K30.0120$62.95172.7M576k20h 0m47315
84Qwen3.8-Max0.0118$16.9953.1M556k19h 0m4152
85Gemini 3.7 Flash0.0110$6.6319.2M229k5h 4m1665
86Grok 4.60.0106$206.03201.8M768k19h 59m84563
87Claude Opus 50.0105$138.91229.6M656k19h 23m4499
88Muse Spark 1.20.0104$27.73109.9M451k7h 13m35810
89Gemini 3.8 Flash0.0102$13.7978.6M180k10h 32m41111
90Gemini 3.8 Flash0.0100$7.6432.7M97k6h 4m2555
91Qwen3.8-Max0.0098$20.1554.4M994k19h 8m3216
92Gemini 3.8 Flash0.0097$6.8733.3M108k7h 49m2517
93Muse Spark 1.20.0097$69.69161.5M457k8h 41m4415
94Gemini 3.7 Flash0.0097$3.4713.3M97k5h 22m1534
95DeepSeek V4 Flash Vision Exp0.0094$6.17373.9M627k11h 53m7989
96Gemini 3.8 Flash0.0094$15.1581.6M161k9h 26m42511
97Qwen3.8-Max0.0089$23.5477.9M588k18h 20m4032
98Qwen3.8-Max-09020.0087$44.20104.3M2.8M19h 20m3332
99Muse Spark 1.20.0087$13.2553.2M190k6h 44m2953
100DeepSeek V4 Flash Vision Exp0.0081$3.17180.3M434k7h 52m5542
101Qwen3.8-Max-09020.0080$44.17113.8M2.4M19h 47m3371
102Inkling0.0073$7.838.2M21k1h 33m1412
103Muse Spark 1.20.0065$21.1865.3M269k5h 22m3133
104Inkling0.0061$5.435.5M41k1h 2m1472
105Inkling0.0061$13.6714.2M40k2h 24m2252
106GLM-5.3 Flash0.0056$7.03151.5M495k17h 26m37410
107DeepSeek V4 Flash Vision Exp0.0056$3.93222.7M553k14h 38m5307
108Inkling0.0039$4.624.8M24k1h 6m1011
109Inkling0.0030$5.705.9M31k2h 11m1451
110Qwen3.8-Max-09020.0020$43.94119.8M2.1M19h 50m3712

Lean 4 Kernel Type Checker in Pascal

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.51.0000$56.70219.1M1.0M5h 58m5016
2Claude Haiku 5.51.0000$12.16186.9M1.0M4h 28m4234
3Claude Sonnet 5.51.0000$55.34209.5M1.1M7h 29m5416
4Claude Sonnet 5.51.0000$53.61204.3M990k7h 10m4856
5Claude Opus 51.0000$174.84280.2M919k15h 16m71420
6Claude Opus 5.51.0000$41.28133.2M560k3h 31m26313
7Claude Fable 5.11.0000$34.1749.9M378k2h 37m1646
8Claude Opus 51.0000$204.51327.4M1.1M13h 23m74619
9Gemini 4 Argon1.0000$45.6847.8M303k2h 17m1352
10Claude Opus 5.51.0000$71.71241.5M889k6h 55m57321
11Claude Fable 5.11.0000$45.3070.2M418k4h 0m2009
12Gemini 4 Argon1.0000$81.6285.5M322k3h 41m2042
13Claude Fable 51.0000$203.81160.6M603k9h 37m33511
14Claude Opus 5.51.0000$35.94109.8M528k2h 59m2328
15Gemini 4 Argon1.0000$56.5692.0M304k3h 17m2032
16Claude Haiku 5.51.0000$12.93195.5M1.2M5h 31m4595
17Claude Sonnet 5.51.0000$55.03208.1M1.1M6h 24m4957
18Claude Fable 51.0000$201.80156.2M629k7h 5m31912
19Claude Opus 5.51.0000$31.1188.5M510k2h 27m2024
20Claude Opus 5.51.0000$37.66116.3M544k3h 20m2438
21Claude Fable 5.11.0000$34.2250.9M360k1h 59m1598
22Claude Fable 5.11.0000$43.0867.7M379k4h 3m20611
23Claude Fable 5.11.0000$50.9183.1M385k3h 9m2328
24Claude Opus 50.9984$103.75161.1M640k5h 43m3154
25Claude Opus 50.9841$206.83330.5M1.1M10h 19m76112
26Claude Haiku 5.50.9841$12.26189.0M1.0M5h 12m4672
27Claude Haiku 5.50.9841$9.10133.0M903k3h 32m3702
28Claude Fable 50.9841$232.48180.5M725k7h 59m3138
29Claude Sonnet 5.50.9841$56.48214.6M1.1M12h 59m5138
30Claude Haiku 5.50.9841$10.51161.8M906k4h 31m3892
31GPT-6 Astra0.9807$122.0864.3M290k2h 50m2824
32GPT-5.6 Sol0.9807$221.16222.7M429k6h 13m69119
33Gemini 4 Argon0.9807$13.2439.9M250k1h 35m1172
34GPT-6 Astra0.9807$62.9837.7M245k1h 38m2035
35Gemini 4 Argon0.9807$15.0249.2M292k2h 22m1452
36GPT-6 Astra0.9807$123.0561.8M300k2h 8m2603
37GPT-6 Astra0.9791$34.1522.2M179k1h 14m1333
38GPT-6 Astra0.9791$174.6285.4M285k2h 50m3114
39GPT-5.6 Sol0.9791$78.0186.8M272k4h 32m3952
40Muse Spark 1.30.9776$411.77410.4M713k19h 52m7992
41GPT-5.6 Sol0.9757$207.31199.1M381k7h 23m62010
42Claude Opus 50.9635$169.99269.9M940k17h 12m65517
43Grok 4.70.9589$192.69192.9M802k7h 19m7908
44Grok 4.70.9461$478.73472.8M1.7M19h 19m18875
45Gemini 3.7 Flash0.9448$95.08678.0M1.4M19h 49m16601
46Gemini 3.7 Flash0.9361$54.83453.2M1.3M12h 43m12241
47GPT-5.6 Sol0.9339$340.15337.0M382k8h 35m78911
48Kimi K30.9198$192.68537.9M1.4M20h 0m12181
49Grok 4.70.9103$351.92346.3M1.1M20h 0m14256
50Grok 4.70.8682$294.16294.8M1.1M13h 7m12296
51GLM-5.30.8650$139.71481.8M637k18h 8m8596
52GLM-5.30.8372$111.12401.3M867k19h 42m90410
53Kimi K30.8313$155.97405.9M1.5M19h 47m9353
54GPT-5.6 Sol0.7874$397.16404.0M396k8h 54m11347
55Muse Spark 1.30.7421$154.98818.9M1.3M19h 49m18052
56Muse Spark 1.30.5609$411.55416.2M856k19h 58m9591
57GLM-5.3 Flash0.5457$13.38394.6M1.0M13h 39m9395
58Kimi K30.5265$147.65387.7M1.4M20h 2m8941
59GLM-5.3 Flash0.5060$14.37406.2M1.1M16h 35m10013
60Muse Spark 1.30.5029$384.24384.5M940k19h 50m9371
61Kimi K30.4229$171.33477.1M1.3M19h 55m113012
62GLM-5.30.4065$133.87385.6M660k19h 35m6773
63Grok 4.60.3824$105.13105.0M1.0M6h 34m4902
64DeepSeek V4 Flash Vision Exp0.3599$12.71725.7M1.6M10h 38m16144
65Muse Spark 1.30.3530$389.61408.6M860k19h 59m10151
66DeepSeek V4 Flash Vision Exp0.3164$9.48551.4M1.2M7h 58m12288
67GLM-5.3 Flash0.3164$17.89532.1M1.2M17h 29m11984
68Kimi K30.2644$151.43423.8M1.1M20h 1m9281
69DeepSeek V4 Flash Vision Exp0.2513$13.44768.2M1.8M13h 43m17607
70GLM-5.3 Flash0.2321$15.97465.4M1.2M13h 20m104931
71Qwen3.8-Max-09020.1653$45.5698.3M3.3M20h 1m2941
72Gemini 3.7 Flash0.1248$74.81557.5M1.1M14h 22m12171
73GLM-5.30.1056$134.85474.9M964k19h 7m11053
74DeepSeek V4 Flash Vision Exp0.0143$12.56761.2M1.2M12h 33m162735
75Qwen3.8-Max-09020.0111$40.0677.6M3.2M20h 1m2441
76Gemini 3.7 Flash0.0087$48.94384.1M939k13h 20m11181
77Muse Spark 1.20.0000$19.14108.5M529k2h 29m3481
78Qwen3.8-Max0.0000$14.1428.2M1.1M19h 59m1691
79Inkling0.0000$5.565.7M37k1h 16m1152
80Inkling0.0000$5.465.6M34k55m1072
81Muse Spark 1.20.0000$21.0953.6M699k3h 48m2052
82Muse Spark 1.20.0000$29.46162.8M830k6h 1m4043
83Qwen3.8-Max0.0000$8.3110.6M914k19h 59m1092
84Inkling0.0000$5.705.9M22k14m802
85Qwen3.8-Max-09020.0000$35.7344.7M3.0M20h 1m3121
86Grok 4.60.0000$114.14110.5M1.1M7h 47m4924
87Muse Spark 1.20.0000$27.3088.9M859k4h 46m2781
88Grok 4.60.0000$407.54406.7M2.0M19h 47m1527137
89Gemini 3.8 Flash0.0000$90.95821.2M1.4M20h 0m20381
90Grok 4.60.0000$250.10240.1M1.8M13h 13m97043
91Inkling0.0000$13.8114.4M43k1h 26m1751
92Qwen3.8-Max-09020.0000$33.4345.6M3.5M20h 1m1841
93DeepSeek V4 Flash Vision Exp0.0000$11.64694.6M1.3M11h 22m141333
94Claude Fable 50.0000$288.50223.6M888k18h 15m53613
95Grok 4.60.0000$233.84217.8M2.5M19h 53m92930
96Muse Spark 1.20.0000$9.5148.0M382k2h 35m2132
97Grok 4.70.0000$418.16407.2M1.6M18h 42m16407
98Claude Fable 50.0000$144.73104.4M563k6h 16m23513
99GLM-5.3 Flash0.0000$17.57476.0M1.4M17h 22m10235
100Gemini 3.8 Flash0.0000$69.03618.4M870k14h 14m14773
101Gemini 3.8 Flash0.0000$77.67724.4M1.0M15h 44m16762
102Gemini 3.7 Flash0.0000$101.50861.0M1.8M19h 58m20921
103Gemini 3.8 Flash0.0000$82.03739.4M1.1M17h 33m17971
104Qwen3.8-Max0.0000$13.9225.5M1.2M19h 56m1672
105Gemini 3.8 Flash0.0000$66.46629.7M880k14h 44m15993
106Qwen3.8-Max0.0000$19.6845.8M1.3M20h 0m2111
107GLM-5.30.0000$113.59400.7M1.0M18h 31m9625
108Qwen3.8-Max0.0000$10.3513.6M1.1M19h 57m1151
109Qwen3.8-Max-09020.0000$22.2825.4M2.5M14h 13m1511
110Inkling0.0000$6.566.8M25k12m1096

libexpat Optimization

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.8047$233.16850.8M2.4M15h 14m175871
2Claude Fable 50.7799$660.65527.2M1.8M19h 20m125146
3Claude Sonnet 5.50.7156$145.32582.0M2.3M15h 31m125317
4Claude Opus 5.50.7133$179.28606.1M2.3M14h 58m138420
5Claude Sonnet 5.50.7089$104.14409.0M1.8M9h 58m9058
6Claude Opus 5.50.6801$255.81936.5M2.6M17h 42m206487
7Claude Sonnet 5.50.6732$123.96482.0M2.2M17h 39m106421
8Claude Sonnet 5.50.6432$111.15436.3M1.9M12h 32m91114
9Gemini 4 Argon0.6081$51.02180.3M915k5h 20m3888
10Gemini 4 Argon0.5881$18.3871.0M446k2h 16m1609
11Gemini 4 Argon0.5870$86.35125.1M819k4h 40m3404
12Claude Fable 5.10.5674$350.25628.4M1.5M16h 3m145682
13Claude Sonnet 5.50.5673$154.38620.0M2.4M16h 46m13266
14Gemini 4 Argon0.5630$26.2474.9M691k2h 55m1989
15Claude Fable 5.10.5395$313.80554.2M1.5M11h 26m128934
16Claude Opus 50.5365$422.53667.4M2.4M15h 22m149147
17Claude Opus 50.5236$756.501269.1M3.2M19h 11m274394
18Claude Opus 50.5183$561.01908.7M2.8M16h 42m209066
19Claude Opus 50.5083$502.07801.8M2.6M18h 34m185260
20Claude Opus 50.5030$470.72762.4M2.3M16h 43m165645
21Claude Fable 5.10.4885$375.68676.2M1.5M17h 3m150550
22Claude Opus 5.50.4775$212.18685.7M2.9M15h 26m165963
23Claude Opus 5.50.4760$260.62918.4M2.9M17h 55m204364
24Gemini 4 Argon0.4643$17.1966.1M478k2h 17m1584
25Claude Fable 5.10.4469$289.07503.7M1.5M13h 41m115650
26Claude Fable 50.4435$891.44742.6M2.0M15h 20m163982
27GPT-5.6 Sol0.3847$146.13140.6M311k2h 25m4397
28Claude Fable 50.3547$517.42421.8M1.3M18h 48m90236
29Grok 4.70.3527$861.01886.1M3.3M19h 22m3633135
30Claude Fable 50.3358$480.59387.1M1.3M13h 47m84526
31Claude Haiku 5.50.3300$46.90739.9M3.7M9h 50m16277
32GPT-5.6 Sol0.3225$67.0675.3M223k1h 44m3269
33GPT-5.6 Sol0.3025$18.3526.1M127k53m1444
34GPT-6 Astra0.2941$510.01240.5M518k4h 1m5427
35Claude Fable 5.10.2880$179.04308.9M1.0M10h 29m75512
36GPT-5.6 Sol0.2868$49.1153.9M193k1h 32m2385
37GPT-6 Astra0.2776$415.35191.6M517k3h 32m4446
38GPT-5.6 Sol0.2751$110.05104.7M243k2h 24m3507
39GPT-6 Astra0.2744$177.8683.5M336k2h 10m2835
40Claude Fable 50.2667$556.53463.3M1.2M18h 41m91225
41Gemini 3.7 Flash0.2399$41.35394.7M960k4h 30m10096
42GLM-5.30.2372$181.79673.8M1.1M8h 14m15013
43GLM-5.30.2303$183.58670.1M1.1M9h 50m146018
44Claude Haiku 5.50.2257$53.36858.1M3.9M16h 29m182736
45GLM-5.30.1823$327.581209.3M1.8M18h 23m263546
46Kimi K30.1778$238.01679.3M1.8M19h 52m158883
47GLM-5.30.1583$236.28865.5M1.6M18h 53m199134
48Grok 4.70.1576$386.43383.9M880k5h 16m127713
49Gemini 3.7 Flash0.1572$41.30358.7M785k6h 1m8995
50Claude Haiku 5.50.1556$46.19751.2M3.1M15h 48m161016
51Gemini 3.7 Flash0.1555$24.69216.5M877k2h 56m6242
52GPT-6 Astra0.1534$13.196.7M92k53m624
53GPT-6 Astra0.1516$19.3310.3M134k38m783
54Kimi K30.1513$169.56484.2M1.2M19h 34m115516
55Grok 4.60.1479$150.76148.7M804k4h 11m58026
56Grok 4.60.1393$108.10108.1M736k4h 5m43511
57Claude Haiku 5.50.1387$35.67574.8M2.5M9h 45m12828
58Kimi K30.1288$173.14509.0M1.1M13h 23m114928
59Gemini 3.8 Flash0.1280$22.80229.1M416k2h 32m5412
60Gemini 3.8 Flash0.1047$29.07295.3M541k5h 49m7913
61Grok 4.60.1022$79.4275.8M516k2h 56m2737
62Muse Spark 1.30.0996$565.41641.8M1.1M19h 58m142216
63Gemini 3.8 Flash0.0991$27.80282.7M663k2h 44m77117
64DeepSeek V4 Flash Vision Exp0.0891$17.041034.3M1.6M6h 42m22736
65Claude Haiku 5.50.0877$18.92306.6M1.3M3h 20m6498
66Muse Spark 1.30.0752$635.38703.6M636k19h 52m13423
67Gemini 3.8 Flash0.0565$31.04299.7M611k3h 45m8184
68DeepSeek V4 Flash Vision Exp0.0545$16.46992.0M1.7M6h 43m222211
69Muse Spark 1.30.0491$376.252119.7M1.7M19h 47m4639144
70Muse Spark 1.30.0092$609.32704.0M1.1M19h 57m14972
71Qwen3.8-Max-09020.0000$53.45131.0M3.2M20h 1m3781
72Muse Spark 1.20.0000$40.00150.5M651k3h 23m3883
73Muse Spark 1.20.0000$41.66132.7M956k3h 49m4733
74Inkling0.0000$23.4724.5M46k39m3592
75Muse Spark 1.20.0000$16.5487.9M378k1h 23m3093
76Qwen3.8-Max0.0000$21.1536.8M1.9M20h 0m260—
77GLM-5.3 Flash0.0000$22.01646.4M1.1M19h 18m15141
78GLM-5.3 Flash0.0000$23.47725.1M1.2M15h 11m163214
79Inkling0.0000$3.703.7M39k18m852
80Qwen3.8-Max0.0000$16.2822.3M1.7M19h 46m202—
81Gemini 3.7 Flash0.0000$33.92328.7M960k2h 58m81020
82Qwen3.8-Max-09020.0000$42.4890.3M3.1M19h 53m3484
83DeepSeek V4 Flash Vision Exp0.0000$13.51827.8M1.3M5h 43m172013
84DeepSeek V4 Flash Vision Exp0.0000$21.931323.6M2.2M8h 50m30957
85Gemini 3.7 Flash0.0000$29.56325.1M599k2h 10m8302
86GLM-5.3 Flash0.0000$28.19886.8M1.2M17h 12m208325
87DeepSeek V4 Flash Vision Exp0.0000$33.361965.0M3.8M19h 31m410248
88Kimi K30.0000$214.44584.8M1.8M20h 0m14591
89Inkling0.0000$18.3619.0M75k47m2514
90GLM-5.3 Flash0.0000$25.76811.2M1.4M20h 0m24217
91Grok 4.70.0000$77.7179.6M493k2h 16m3254
92Grok 4.70.0000$35.6933.2M254k1h 17m1395
93Qwen3.8-Max0.0000$19.2333.9M1.7M19h 53m2331
94Qwen3.8-Max-09020.0000$36.1560.0M3.4M20h 0m2803
95Grok 4.60.0000$93.7799.5M677k3h 26m43510
96Muse Spark 1.20.0000$39.83172.4M582k3h 18m5596
97Qwen3.8-Max-09020.0000$95.18281.1M3.9M19h 0m6323
98Inkling0.0000$3.583.6M31k16m742
99Qwen3.8-Max0.0000$25.1246.8M2.2M19h 55m301—
100Gemini 3.8 Flash0.0000$35.42341.5M629k6h 5m9072
101Qwen3.8-Max-09020.0000$38.4273.2M3.2M20h 0m3402
102Muse Spark 1.20.0000$32.92157.9M806k3h 52m3443
103Grok 4.60.0000$71.7870.3M399k1h 58m2775
104GLM-5.3 Flash0.0000$21.51630.1M971k19h 59m14582
105Qwen3.8-Max0.0000$13.0614.1M1.6M19h 35m156—
106Inkling0.0000$3.113.2M24k13m823
107Kimi K30.0000$256.75739.1M1.4M20h 0m15761
108Muse Spark 1.30.0000$571.21716.3M974k19h 59m16832
109GLM-5.30.0000$216.67774.3M1.6M16h 7m175419
110Grok 4.70.0000†$83.0379.6M516k2h 36m31413

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Lua Native Compiler

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Argon1.0000$73.2990.2M317k3h 26m2122
2Claude Sonnet 5.51.0000$63.17240.2M1.2M8h 33m5744
3Claude Fable 5.11.0000$44.1969.8M381k3h 24m2158
4Claude Fable 5.11.0000$51.0382.5M402k3h 56m24512
5Claude Sonnet 5.51.0000$62.32242.2M1.1M9h 42m62010
6GPT-6 Astra1.0000$46.1926.4M213k1h 23m1347
7Claude Sonnet 5.51.0000$65.89255.0M1.2M8h 21m6303
8Claude Fable 51.0000$196.16153.6M590k6h 11m3516
9Claude Haiku 5.51.0000$21.88349.5M1.7M12h 38m80516
10Claude Opus 51.0000$209.27343.2M992k13h 38m82610
11Claude Opus 51.0000$125.36207.5M580k6h 45m4269
12Claude Fable 5.11.0000$55.8488.8M470k3h 14m2356
13Claude Haiku 5.51.0000$14.18224.8M1.1M5h 49m5543
14Claude Opus 51.0000$155.19264.1M628k9h 49m49411
15Claude Sonnet 5.51.0000$84.18344.6M1.2M16h 46m74614
16GPT-6 Astra1.0000$35.9723.6M186k1h 21m1334
17GPT-6 Astra1.0000$131.7664.1M279k2h 36m2327
18Claude Opus 50.9992$107.50172.4M579k5h 52m3754
19Claude Opus 50.9992$128.06213.3M585k7h 58m4542
20Gemini 4 Argon0.9976$24.6660.9M275k2h 36m1372
21Gemini 4 Argon0.9976$34.7250.2M259k2h 22m1362
22Gemini 4 Argon0.9976$36.9359.8M371k3h 58m1542
23GLM-5.30.9976$201.34735.2M1.4M11h 37m16603
24GPT-6 Astra0.9976$79.5942.6M240k2h 8m1959
25Claude Haiku 5.50.9976$23.67398.7M1.3M8h 23m8197
26Gemini 4 Argon0.9976$21.7152.8M265k2h 10m1422
27Muse Spark 1.30.9976$451.94515.6M941k16h 46m12612
28GPT-6 Astra0.9976$93.6948.6M237k1h 56m2066
29GLM-5.30.9953$142.13511.6M1.2M9h 22m11782
30DeepSeek V4 Flash Vision Exp0.9788$23.061383.4M2.4M13h 19m291121
31GLM-5.30.9599$274.761000.1M1.8M19h 32m22735
32Kimi K30.9575$183.51524.3M1.3M19h 59m120320
33GLM-5.30.9527$236.30883.7M1.1M17h 20m18357
34Claude Haiku 5.50.9292$10.74177.0M661k2h 38m3281
35Kimi K30.8750$185.22530.7M1.3M20h 0m12071
36Claude Fable 5.10.8463$43.7869.0M381k3h 39m2311
37Claude Opus 5.50.7885$68.38213.8M1.0M9h 38m48211
38Gemini 3.8 Flash0.7382$43.93463.1M839k6h 53m11361
39Gemini 3.7 Flash0.6998$21.69183.4M580k2h 58m4001
40Claude Fable 50.6667$216.90168.1M672k7h 17m3375
41Claude Fable 50.6667$173.23133.0M557k7h 50m2928
42Claude Fable 5.10.6667$57.3892.1M466k4h 40m2487
43Claude Haiku 5.50.6667$17.99286.4M1.3M10h 1m6614
44Claude Opus 5.50.6667$78.97234.5M1.3M9h 24m64915
45Gemini 3.7 Flash0.6541$62.39519.3M1.2M7h 8m12601
46Gemini 3.7 Flash0.6517$26.08255.3M824k1h 58m6701
47Claude Opus 5.50.6447$81.59228.2M1.4M10h 19m6078
48Gemini 3.7 Flash0.6392$29.13278.2M822k3h 5m7511
49Grok 4.60.6384$176.45167.1M1.5M7h 26m6538
50Kimi K30.5063$220.93645.6M1.2M20h 2m14611
51Muse Spark 1.30.4969$541.57625.6M1.2M20h 0m14471
52Muse Spark 1.30.4002$540.38602.2M792k20h 0m14001
53GLM-5.3 Flash0.3625$33.261014.3M1.2M20h 1m20021
54Gemini 3.7 Flash0.3270$79.34743.6M1.7M8h 42m18151
55Kimi K30.2862$159.88431.8M1.4M19h 11m10091
56Claude Fable 50.2123$203.21167.2M496k10h 45m40211
57DeepSeek V4 Flash Vision Exp0.2005$21.271250.2M2.4M15h 16m267617
58GLM-5.3 Flash0.1899$23.36672.0M1.1M19h 59m15303
59GLM-5.3 Flash0.0339$26.65828.1M1.4M19h 57m19842
60Inkling0.0000$27.7428.9M72k42m3001
61Grok 4.70.0000$74.2476.4M456k2h 25m3731
62Inkling0.0000$16.9217.5M67k44m2211
63Claude Sonnet 5.50.0000$70.29272.9M1.3M13h 50m6495
64Grok 4.70.0000$23.4623.7M161k55m1211
65Qwen3.8-Max0.0000$64.51206.8M2.0M19h 8m6392
66GLM-5.3 Flash0.0000$24.51738.8M1.3M18h 5m154529
67DeepSeek V4 Flash Vision Exp0.0000$11.39676.4M1.3M7h 45m150715
68Claude Fable 50.0000$255.17207.7M659k6h 43m4268
69Grok 4.60.0000$110.36107.0M986k5h 11m4478
70Muse Spark 1.30.0000†$75.32109.8M406k5h 42m4616
71Inkling0.0000$48.6250.6M132k1h 1m3672
72GPT-5.6 Sol0.0000$35.0744.0M172k2h 41m21110
73Muse Spark 1.20.0000$44.95118.1M616k6h 24m3542
74Qwen3.8-Max-09020.0000$32.3939.9M3.6M20h 0m2061
75Kimi K30.0000$228.55670.7M1.4M19h 8m14083
76Qwen3.8-Max-09020.0000$40.9173.7M3.6M19h 57m2721
77Inkling0.0000$14.8115.3M75k53m2231
78Claude Opus 5.50.0000$124.07397.7M1.8M12h 35m89328
79GPT-5.6 Sol0.0000†$7.458.9M65k25m653
80GLM-5.30.0000$251.10909.6M1.3M19h 55m19186
81Gemini 3.8 Flash0.0000†$7.6674.9M188k44m3042
82Qwen3.8-Max0.0000$121.10426.7M2.2M19h 59m9841
83Claude Opus 5.50.0000$93.26296.3M1.3M8h 6m67312
84Grok 4.60.0000$271.55264.4M2.0M9h 49m106131
85Muse Spark 1.20.0000$10.7739.0M388k1h 41m1644
86DeepSeek V4 Flash Vision Exp0.0000$22.431385.4M2.0M11h 31m28602
87GLM-5.3 Flash0.0000$31.03962.8M1.5M19h 47m216010
88Gemini 3.8 Flash0.0000†$9.1088.8M213k1h 38m3282
89Qwen3.8-Max0.0000$135.25480.8M2.3M19h 7m10812
90Qwen3.8-Max0.0000$60.45189.1M2.1M19h 48m5993
91Grok 4.70.0000$84.7885.6M413k2h 11m3303
92Qwen3.8-Max0.0000$31.0087.6M1.4M13h 21m3856
93Qwen3.8-Max-09020.0000$31.8833.4M3.8M20h 13m2091
94Inkling0.0000$7.918.2M23k26m1652
95Grok 4.60.0000$676.54663.0M4.1M19h 59m2429277
96Gemini 3.8 Flash0.0000†$23.38246.7M422k1h 50m6821
97GPT-5.6 Sol0.0000$127.72124.4M217k2h 5m38224
98Muse Spark 1.20.0000$4.4622.6M149k52m1452
99Muse Spark 1.30.0000$637.70724.8M869k20h 0m16311
100DeepSeek V4 Flash Vision Exp0.0000$18.341059.5M2.2M17h 1m23839
101Qwen3.8-Max-09020.0000$34.7650.3M3.5M20h 2m2511
102GPT-5.6 Sol0.0000$24.8437.1M163k1h 9m21913
103Grok 4.60.0000$250.76240.6M2.1M11h 13m93016
104Grok 4.70.0000$10.1812.5M117k39m811
105Muse Spark 1.20.0000$22.61124.4M368k1h 49m3232
106Muse Spark 1.20.0000$12.0053.2M328k1h 52m1892
107Grok 4.70.0000$15.5217.3M144k46m1031
108Gemini 3.8 Flash0.0000†$32.38312.3M482k4h 4m8321
109Qwen3.8-Max-09020.0000$91.51260.0M4.2M19h 42m5781
110GPT-5.6 Sol0.0000$20.5039.9M168k1h 9m2317

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Machine-Learned Interatomic Potential

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.9988$28.90111.3M520k17h 22m2987
2Claude Opus 5.50.9986$19.9256.8M329k17h 53m2179
3Claude Sonnet 5.50.9974$29.98117.0M513k18h 55m3032
4Gemini 4 Argon0.9973$144.92105.5M303k19h 54m27310
5Claude Haiku 5.50.9960$3.0744.7M342k18h 31m1813
6Claude Haiku 5.50.9949$5.3885.9M416k15h 26m2743
7Gemini 4 Argon0.9944$61.2455.2M244k20h 19m18914
8Gemini 4 Argon0.9938$60.3445.2M281k20h 31m16713
9Gemini 4 Argon0.9931$56.1857.5M250k20h 47m20910
10Qwen3.8-Max-09020.9925$42.93126.0M1.3M20h 0m6172
11GPT-5.6 Sol0.9925$108.64109.2M151k11h 16m3488
12GPT-5.6 Sol0.9918$109.29114.5M152k15h 47m40416
13GLM-5.30.9901$21.3550.8M160k19h 5m3531
14Claude Haiku 5.50.9898$6.24101.6M445k15h 29m3043
15GPT-6 Astra0.9884$148.0172.8M245k17h 13m2838
16GPT-6 Astra0.9884$97.1352.7M210k16h 8m2576
17Qwen3.8-Max-09020.9860$42.29135.8M786k19h 35m5352
18GPT-6 Astra0.9842$127.3365.0M249k17h 10m2877
19Gemini 4 Argon0.9823$48.4349.9M216k20h 21m19920
20Claude Opus 50.9772$29.8238.2M293k18h 29m1722
21Muse Spark 1.30.9755$18.5916.6M98k19h 46m2193
22Qwen3.8-Max0.9731$4.1011.4M180k17h 54m1853
23GPT-6 Astra0.9702$43.8726.5M154k17h 20m1529
24GPT-6 Astra0.9688$90.0151.8M262k15h 58m2867
25Claude Fable 50.9674$40.4026.4M189k18h 39m1817
26Muse Spark 1.30.9671$61.9258.4M240k19h 36m4104
27Claude Opus 5.50.9657$21.3260.2M359k15h 52m2197
28GLM-5.3 Flash0.9637$1.5238.6M196k15h 9m2532
29GLM-5.30.9615$15.6237.8M156k19h 29m2942
30Grok 4.70.9608$60.4536.2M244k15h 59m1872
31Grok 4.70.9588$76.2457.2M274k16h 2m23812
32Claude Fable 5.10.9586$14.2221.7M140k16h 34m17911
33Claude Opus 5.50.9563$17.1548.3M286k18h 37m1968
34Grok 4.70.9549$72.0345.6M246k19h 9m2157
35Claude Opus 50.9539$25.7331.4M274k19h 1m16010
36Muse Spark 1.30.9529$5.4710.6M104k19h 34m1772
37Grok 4.70.9454$102.7267.6M289k18h 50m2548
38GPT-5.6 Sol0.9437$26.2041.3M108k14h 19m2373
39Claude Fable 5.10.9369$12.1118.4M119k17h 11m17515
40Kimi K30.9282$14.8121.6M194k19h 20m1753
41Qwen3.8-Max-09020.9269$37.45125.1M855k19h 28m4941
42Qwen3.8-Max0.9220$5.1315.3M180k19h 14m2092
43Claude Opus 5.50.9209$19.0056.2M297k18h 34m23112
44GLM-5.30.9184$31.3162.0M243k18h 46m3072
45Kimi K30.9177$11.7220.5M161k18h 47m1653
46DeepSeek V4 Flash Vision Exp0.9173$3.12179.4M413k18h 25m5586
47Claude Opus 50.9168$37.6849.7M354k18h 11m1878
48Claude Haiku 5.50.9161$2.2530.2M316k15h 29m1343
49Qwen3.8-Max-09020.9150$18.3354.0M689k20h 5m3231
50Claude Fable 5.10.9113$11.2616.5M124k17h 50m1505
51Claude Fable 50.9086$35.5921.8M190k19h 5m1484
52Gemini 3.8 Flash0.9006$5.1942.9M142k3h 20m2586
53Grok 4.60.8964$27.9418.3M258k19h 42m1472
54Kimi K30.8916$6.549.0M95k18h 28m1262
55Muse Spark 1.20.8888$4.0820.1M191k2h 11m16512
56Claude Fable 50.8825$22.8713.4M129k19h 3m1346
57Claude Fable 5.10.8820$17.0526.5M157k16h 32m1797
58Grok 4.60.8799$71.4258.5M227k19h 56m3079
59Muse Spark 1.20.8642$31.30153.8M371k2h 47m46412
60Gemini 3.8 Flash0.8493$4.8137.8M168k3h 17m2325
61Gemini 3.7 Flash0.8422$11.4530.2M159k8h 5m2083
62Muse Spark 1.30.8349$17.6515.6M188k19h 8m1741
63Grok 4.60.8342$80.8855.9M251k19h 37m26510
64Claude Fable 5.10.8229$11.9918.2M119k18h 9m17113
65Muse Spark 1.20.8223$3.4515.9M178k49m1273
66GLM-5.30.8163$20.3255.4M207k19h 30m3502
67Qwen3.8-Max0.8093$6.9420.8M251k18h 48m2312
68Kimi K30.8033$15.1121.0M176k19h 11m1683
69Claude Fable 50.8027$24.7614.6M137k19h 30m1337
70GLM-5.30.7858$25.2849.5M200k18h 31m2852
71Muse Spark 1.20.7533$3.6517.8M164k1h 53m1263
72Kimi K30.7378$9.8813.2M119k19h 28m1432
73Gemini 3.7 Flash0.7285$10.9529.5M154k8h 16m2137
74Grok 4.60.7267$28.2320.6M259k19h 44m1593
75Muse Spark 1.20.7264$3.5517.0M170k2h 17m1443
76Claude Haiku 5.50.6983$3.4651.0M368k17h 19m1921
77DeepSeek V4 Flash Vision Exp0.6906$1.8093.9M332k18h 0m3786
78Qwen3.8-Max-09020.6529$37.06123.0M877k19h 28m4482
79Claude Opus 50.5927$30.9639.3M312k17h 25m1843
80Grok 4.60.5686$61.5946.3M291k18h 29m2504
81Gemini 3.7 Flash0.5113$8.2127.8M178k5h 29m1842
82DeepSeek V4 Flash Vision Exp0.4712$1.0554.4M192k19h 29m3422
83Claude Opus 5.50.4697$23.4366.1M395k18h 40m2328
84Gemini 3.7 Flash0.4203$5.2521.8M116k4h 45m1781
85Muse Spark 1.30.2516$58.4551.9M245k19h 22m3575
86DeepSeek V4 Flash Vision Exp0.2438$1.5984.5M269k19h 1m3895
87Qwen3.8-Max0.2071$6.2316.9M295k18h 26m2182
88Gemini 3.8 Flash0.0997$3.7323.7M117k2h 23m1946
89Claude Sonnet 5.50.0768$45.32189.2M581k18h 26m41410
90Inkling0.0572$3.463.5M36k2h 37m1361
91DeepSeek V4 Flash Vision Exp0.0562$2.23120.5M374k18h 41m4363
92Gemini 3.8 Flash0.0439$5.1542.3M159k2h 44m2603
93Inkling0.0431$4.945.0M59k45m1201
94Inkling0.0393$6.847.0M43k1h 26m1811
95Claude Fable 50.0239$24.8514.9M135k19h 4m1437
96Claude Sonnet 5.50.0201$40.13162.7M594k17h 49m3567
97Inkling0.0179$5.355.4M56k1h 32m1262
98Inkling0.0126$4.985.1M42k1h 33m1482
99GPT-5.6 Sol0.0076$48.9956.5M122k14h 29m2935
100Claude Sonnet 5.50.0058$42.44171.8M631k18h 38m3721
101GPT-5.6 Sol0.0010$36.5549.8M109k7h 20m2723
102Qwen3.8-Max0.0010$4.4112.0M206k19h 18m1791
103Gemini 3.7 Flash0.0010$6.0120.4M174k4h 35m1542
104Gemini 3.8 Flash0.0009$42.37149.3M250k10h 22m41510
105Claude Opus 50.0000$33.2446.7M272k18h 15m2336
106GLM-5.3 Flash0.0000$1.8927.2M201k18h 44m1973
107Grok 4.70.0000$87.6566.0M273k12h 6m26015
108GLM-5.3 Flash0.0000$1.7624.4M187k19h 19m1852
109GLM-5.3 Flash0.0000$2.2940.6M258k17h 24m2214
110GLM-5.3 Flash0.0000$1.9227.6M178k19h 14m2165

Medium-Range Weather Forecast

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.6553$21.3171.4M261k19h 12m31310
2Claude Sonnet 5.50.6529$36.04148.8M488k17h 33m4011
3GPT-6 Astra0.6474$297.67145.6M335k19h 47m44114
4Claude Sonnet 5.50.6443$32.66133.0M473k13h 39m3829
5Claude Opus 5.50.6405$16.7650.5M249k15h 23m25011
6GPT-6 Astra0.6387$27.5517.3M152k18h 9m13512
7Claude Opus 5.50.6368$21.6471.5M273k18h 3m28810
8GPT-6 Astra0.6362$98.7753.1M216k17h 56m25714
9GPT-6 Astra0.6334$244.67123.1M350k18h 49m44513
10Claude Opus 50.6321$37.3953.5M286k19h 19m23811
11Claude Opus 5.50.6263$14.1142.0M214k18h 26m2257
12Claude Fable 5.10.6214$15.1124.2M125k16h 58m20411
13Grok 4.70.6200$170.45150.1M788k19h 40m61921
14Claude Sonnet 5.50.6188$32.99135.6M450k18h 0m39414
15Claude Fable 5.10.6178$12.6920.4M104k18h 1m17512
16Claude Sonnet 5.50.6171$43.64183.7M536k18h 29m4475
17Claude Opus 5.50.6141$21.3770.5M271k17h 20m29812
18Claude Sonnet 5.50.6027$41.54172.7M541k18h 15m4239
19Claude Opus 50.6013$44.2866.4M300k18h 19m2978
20Claude Fable 5.10.6011$16.8127.4M129k16h 5m20816
21Claude Fable 5.10.5960$16.0625.6M135k16h 36m19312
22GPT-5.6 Sol0.5936$28.8247.8M113k15h 13m2944
23Grok 4.70.5877$164.64141.5M437k18h 53m59629
24GLM-5.30.5873$22.6171.9M228k18h 20m3142
25Claude Fable 50.5825$47.7632.3M210k18h 28m19910
26Claude Opus 50.5817$68.20109.3M364k18h 25m36915
27Grok 4.60.5804$120.40104.0M444k19h 13m46437
28Gemini 3.8 Flash0.5769$6.4456.5M193k2h 43m27511
29Gemini 3.7 Flash0.5747$22.4049.9M145k13h 34m2567
30Gemini 4 Argon0.5653$75.4253.6M408k7h 44m1629
31Claude Haiku 5.50.5631$7.09116.4M474k17h 27m3329
32GLM-5.3 Flash0.5584$3.6151.8M199k18h 29m2842
33Claude Haiku 5.50.5581$5.3484.1M425k18h 46m27210
34Gemini 3.7 Flash0.5566$16.5654.7M160k9h 58m2852
35Grok 4.60.5522$208.02184.0M911k19h 55m82653
36Grok 4.60.5495$238.57230.6M626k20h 0m86162
37Claude Opus 50.5405$40.4059.3M291k18h 27m26116
38Gemini 3.7 Flash0.5365$13.1137.7M147k6h 21m2413
39Gemini 3.7 Flash0.5356$19.3648.1M172k8h 5m2524
40Gemini 4 Argon0.5347$151.2388.8M463k15h 22m23910
41Grok 4.70.5339$192.06177.7M824k19h 10m75817
42Gemini 3.7 Flash0.5332$4.9921.4M136k4h 20m1711
43Gemini 3.8 Flash0.5330$4.1232.2M140k2h 31m1975
44GLM-5.3 Flash0.5292$1.7130.3M154k17h 56m2225
45Gemini 3.8 Flash0.5214$13.5489.8M215k6h 8m39014
46Claude Fable 50.5192$49.6235.7M184k19h 9m2258
47Claude Haiku 5.50.5171$4.7273.7M409k16h 51m2541
48Qwen3.8-Max-09020.5127$30.58103.4M640k19h 23m4491
49Claude Fable 50.5126$51.6934.8M233k18h 40m21914
50Gemini 3.8 Flash0.4927$3.7130.1M141k2h 9m1832
51Claude Haiku 5.50.4915$6.89111.9M491k13h 38m3283
52Claude Fable 50.4845$59.3044.0M208k17h 47m2596
53Claude Fable 50.4839$57.2042.6M198k18h 53m2589
54Gemini 4 Argon0.4825$53.2850.9M579k8h 27m1594
55GLM-5.30.4818$19.7547.5M201k18h 1m2735
56GLM-5.30.4745$28.0396.3M327k19h 20m3637
57GLM-5.30.4723$21.0347.8M206k18h 36m2932
58Claude Haiku 5.50.4720$4.5474.1M339k17h 59m2761
59Gemini 4 Argon0.4704$122.3082.4M652k20h 41m19310
60GLM-5.30.4679$26.3077.9M252k19h 29m3642
61Muse Spark 1.30.4646$17.4032.8M150k19h 29m25011
62Qwen3.8-Max-09020.4642$26.0487.1M568k18h 55m4012
63DeepSeek V4 Flash Vision Exp0.4639$1.5583.0M253k19h 5m4035
64GLM-5.3 Flash0.4629$3.9371.7M248k18h 47m3382
65Grok 4.60.4530$43.0735.9M245k19h 35m2251
66Qwen3.8-Max-09020.4423$42.33144.4M856k19h 32m5481
67Grok 4.70.4365$22.8623.1M216k4h 0m1303
68Muse Spark 1.30.4252$39.9763.7M234k18h 47m40110
69Grok 4.70.4219$34.8931.9M250k3h 58m13511
70Grok 4.60.4154$92.4866.7M263k19h 27m3036
71Muse Spark 1.30.4057$47.0341.9M228k13h 41m31111
72Qwen3.8-Max0.4005$8.9429.1M230k19h 22m2811
73Qwen3.8-Max0.3989$14.9148.7M387k19h 25m3571
74Muse Spark 1.30.3909$44.6041.6M175k17h 28m2837
75Gemini 3.8 Flash0.3886$4.3733.2M181k2h 4m2006
76GLM-5.3 Flash0.3763$2.8373.4M262k16h 13m34313
77Qwen3.8-Max0.3606$13.1244.7M268k19h 18m3853
78GLM-5.3 Flash0.3496$2.9885.3M281k19h 32m3944
79Muse Spark 1.20.3456$4.3818.4M145k37m1042
80Qwen3.8-Max-09020.3435$56.59197.4M966k18h 25m5186
81Qwen3.8-Max0.3410$4.9114.6M172k18h 25m1894
82Qwen3.8-Max0.3360$8.0125.7M213k18h 56m2398
83Muse Spark 1.20.3227$38.37235.4M385k2h 26m5925
84Muse Spark 1.30.3160$38.6381.9M260k18h 49m43413
85Muse Spark 1.20.3018$11.6245.2M202k1h 9m1817
86Muse Spark 1.20.2944$2.128.7M99k50m861
87Muse Spark 1.20.2758$11.1751.5M378k2h 40m2116
88Inkling0.2568$3.543.6M37k1h 43m971
89Inkling0.2237$3.913.9M47k1h 43m1201
90Inkling0.1542$5.245.4M39k1h 50m1322
91Inkling0.1482$3.493.6M19k1h 32m1021
92GPT-5.6 Sol0.0000$122.35137.1M209k17h 41m5767
93GPT-6 Astra0.0000$488.12238.0M474k17h 46m61016
94Kimi K30.0000$20.2549.9M257k19h 31m2968
95Kimi K30.0000$16.0342.3M172k19h 35m2821
96Kimi K30.0000$13.2932.3M193k19h 22m2452
97Gemini 4 Argon0.0000$44.5935.1M340k6h 53m1445
98Inkling0.0000$6.206.2M72k38m1321
99DeepSeek V4 Flash Vision Exp0.0000$1.6690.1M258k19h 29m3923
100Claude Opus 50.0000$33.3646.8M269k19h 5m2295
101DeepSeek V4 Flash Vision Exp0.0000$1.99110.4M289k18h 13m4874
102DeepSeek V4 Flash Vision Exp0.0000$1.5584.2M243k18h 42m3985
103GPT-5.6 Sol0.0000$63.6270.4M130k17h 56m2903
104Kimi K30.0000$11.0428.1M135k19h 31m2616
105GPT-5.6 Sol0.0000$72.5794.1M189k15h 53m47814
106DeepSeek V4 Flash Vision Exp0.0000$1.6893.8M242k19h 27m4522
107Claude Fable 5.10.0000$14.6023.4M121k14h 28m1868
108Qwen3.8-Max-09020.0000$27.2586.2M783k19h 31m3893
109GPT-5.6 Sol0.0000$88.96100.2M138k14h 52m4168
110Kimi K30.0000$19.0948.5M196k18h 52m3266

MEG Speech Decoding

task page →103 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.3980$50.51215.5M568k17h 35m47511
2GPT-6 Astra0.3919$899.22430.4M993k17h 31m106415
3Gemini 4 Argon0.3815$127.6583.3M493k10h 58m2197
4GPT-6 Astra0.3729$274.60132.9M344k8h 16m41113
5Claude Opus 5.50.3727$24.0681.6M282k17h 26m30314
6GPT-6 Astra0.3704$154.2876.5M270k4h 15m2979
7Claude Opus 5.50.3678$32.59115.1M354k17h 32m35313
8Claude Opus 5.50.3676$34.48123.3M365k14h 56m39316
9Muse Spark 1.30.3657$29.6328.5M123k19h 14m29012
10Claude Haiku 5.50.3592$3.5753.4M356k17h 25m2051
11Claude Opus 50.3591$41.2557.4M336k16h 38m24411
12Claude Haiku 5.50.3589$6.1699.7M434k15h 47m3121
13GPT-6 Astra0.3557$452.78217.0M444k15h 46m52714
14Gemini 4 Argon0.3541$66.6565.7M370k10h 16m2086
15Gemini 4 Argon0.3496$73.6173.2M523k11h 46m2159
16GPT-6 Astra0.3431$526.36253.0M673k17h 55m69420
17Claude Sonnet 5.50.3387$39.17161.4M527k11h 58m3742
18Claude Sonnet 5.50.3362$42.30176.9M528k15h 36m4072
19Claude Sonnet 5.50.3295$44.28184.1M576k15h 25m4331
20Gemini 4 Argon0.3253$89.4063.7M382k14h 54m1957
21Claude Haiku 5.50.3229$5.5286.2M451k9h 19m2653
22Claude Opus 50.3182$39.6657.3M295k17h 37m2583
23Claude Fable 5.10.3166$19.4430.2M179k16h 28m2148
24Claude Fable 5.10.3123$26.3542.8M204k16h 51m24012
25GPT-5.6 Sol0.3119$41.2143.5M133k5h 23m2042
26Claude Fable 5.10.3116$13.9921.5M133k17h 11m19211
27Claude Sonnet 5.50.3091$43.33180.7M552k16h 17m43614
28Claude Fable 5.10.3057$16.5726.2M144k13h 23m20211
29Grok 4.60.3041$128.46122.4M984k15h 5m54523
30GPT-5.6 Sol0.3039$14.1019.5M85k2h 25m1372
31Claude Opus 50.3001$47.8268.3M371k18h 4m25114
32Claude Opus 5.50.2944$25.4787.0M298k19h 1m29814
33Claude Fable 50.2869$40.9327.8M172k18h 49m1977
34Claude Fable 50.2738$32.5721.0M153k17h 28m1767
35Claude Haiku 5.50.2649$5.0078.8M385k13h 42m2501
36Claude Haiku 5.50.2545$5.8188.4M483k16h 59m2516
37Claude Fable 50.2462$69.1351.5M236k18h 13m27810
38GPT-5.6 Sol0.2311$153.75128.1M180k10h 45m29817
39Grok 4.60.2265$217.69204.9M1.2M19h 25m87823
40GLM-5.30.2244$22.6851.0M188k18h 6m3152
41Claude Fable 5.10.2155$25.9841.7M212k14h 56m23710
42Grok 4.60.2107$132.86129.3M708k19h 25m57133
43GLM-5.30.2036$34.9674.2M244k14h 55m3722
44GLM-5.3 Flash0.2035$2.3939.2M192k18h 35m2533
45Gemini 4 Argon0.1941$62.2252.9M318k10h 43m1825
46Claude Opus 5.50.1928$24.2378.6M314k16h 53m2819
47GPT-5.6 Sol0.1902$64.3567.7M163k7h 2m2794
48Qwen3.8-Max-09020.1889$35.75119.7M797k19h 10m4702
49Qwen3.8-Max-09020.1871$50.73177.9M853k19h 26m5921
50GPT-5.6 Sol0.1862$104.8098.3M165k7h 53m3188
51Grok 4.60.1844$95.1683.3M284k18h 58m36211
52DeepSeek V4 Flash Vision Exp0.1749$1.3268.7M240k18h 36m3596
53Grok 4.70.1697$27.4625.8M199k3h 25m1335
54Muse Spark 1.20.1659$17.1036.3M144k3h 7m1306
55GLM-5.30.1492$27.3490.5M318k15h 42m3713
56Qwen3.8-Max0.1460$13.1843.8M302k19h 37m3337
57Muse Spark 1.30.1430$33.9830.2M124k18h 44m2784
58Claude Fable 50.1418$35.1322.9M161k18h 17m1767
59GLM-5.3 Flash0.1356$1.9744.0M221k9h 31m2774
60Muse Spark 1.30.1334$8.5030.2M106k18h 10m3177
61Claude Opus 50.1306$32.6545.8M261k17h 4m2329
62Claude Fable 50.1281$60.5443.7M223k17h 15m24911
63Qwen3.8-Max-09020.1258$56.59193.9M1.1M18h 55m5614
64Grok 4.60.1245$71.3867.2M365k9h 53m29310
65GLM-5.3 Flash0.1202$2.0238.5M189k18h 41m2724
66Muse Spark 1.30.1187$59.1456.9M180k14h 50m3673
67Muse Spark 1.20.1175$9.5247.7M272k3h 44m1838
68Gemini 3.7 Flash0.1130$4.8733.1M132k3h 51m2261
69Gemini 3.7 Flash0.1121$12.1251.3M122k7h 24m3124
70Kimi K30.1102$14.9032.2M173k18h 22m2543
71GLM-5.3 Flash0.1039$3.7697.3M271k17h 33m4312
72GLM-5.30.1032$33.8077.7M262k19h 7m3532
73Gemini 3.8 Flash0.1012$4.2232.1M134k3h 25m2203
74Muse Spark 1.20.1011$11.9661.9M415k4h 37m2413
75Qwen3.8-Max0.0985$20.4770.2M412k18h 53m4782
76Gemini 3.8 Flash0.0958$3.9029.7M119k2h 37m2023
77Gemini 3.7 Flash0.0948$9.9338.7M111k7h 46m2665
78Qwen3.8-Max-09020.0904$20.1552.8M623k19h 46m2792
79Gemini 3.7 Flash0.0854$10.1135.8M110k7h 53m3031
80DeepSeek V4 Flash Vision Exp0.0826$1.7393.5M273k12h 25m4572
81Gemini 3.8 Flash0.0714$6.7837.1M131k5h 53m2354
82GLM-5.30.0000$49.90134.3M340k19h 4m46921
83GLM-5.3 Flash0.0000$1.1735.7M150k19h 11m2774
84Muse Spark 1.30.0000$32.8629.1M146k18h 59m2696
85Qwen3.8-Max0.0000$13.8445.7M331k19h 21m3362
86Inkling0.0000$5.295.5M26k1h 28m1511
87Grok 4.70.0000$17.0116.9M171k3h 5m1102
88Grok 4.70.0000$33.7429.5M210k5h 34m1575
89Qwen3.8-Max0.0000$27.9699.7M412k19h 32m5274
90Muse Spark 1.20.0000$13.1177.0M195k5h 0m2023
91Inkling0.0000$5.015.2M28k1h 29m1281
92Qwen3.8-Max-09020.0000$24.1867.0M860k20h 1m3411
93Gemini 3.7 Flash0.0000$12.2048.7M173k7h 50m2852
94Grok 4.70.0000$9.8211.5M148k1h 49m852
95Muse Spark 1.20.0000$16.3673.7M275k2h 42m2447
96Gemini 3.8 Flash0.0000$6.0139.8M130k3h 31m2547
97Inkling0.0000$6.236.3M53k2h 6m1391
98Gemini 3.8 Flash0.0000$6.6641.6M150k3h 57m2516
99Qwen3.8-Max0.0000$8.5526.2M281k19h 56m2421
100Grok 4.70.0000$32.9932.5M199k5h 31m1814
101Inkling0.0000$5.315.5M23k2h 3m1342
102Claude Opus 50.0000$41.1859.8M304k17h 59m2679
103Inkling0.0000$5.425.6M24k1h 30m1161

MS/MS De Novo Generation

task page →100 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.1731$851.54402.0M882k16h 28m92815
2GPT-6 Astra0.1695$1429.90682.5M1.4M13h 9m163115
3GPT-6 Astra0.1667$818.15390.6M876k18h 17m98821
4GPT-6 Astra0.1525$440.96211.9M461k8h 1m5467
5Gemini 4 Argon0.1524$41.9158.1M431k9h 28m1825
6GPT-6 Astra0.1519$408.97200.1M427k5h 57m5745
7Claude Sonnet 5.50.1449$60.59259.5M700k17h 10m5004
8Claude Opus 5.50.1412$32.15111.5M374k16h 42m36712
9Claude Opus 50.1388$55.4079.2M435k18h 4m2477
10Claude Opus 5.50.1378$36.38124.0M438k17h 32m35911
11Claude Sonnet 5.50.1364$65.26259.5M1.1M17h 13m61611
12Claude Opus 50.1349$50.1672.9M377k16h 47m2626
13GPT-5.6 Sol0.1316$55.6569.9M170k12h 29m3322
14GPT-5.6 Sol0.1312$87.71101.7M199k15h 19m4536
15Gemini 4 Argon0.1303$43.3966.9M512k10h 28m1957
16Claude Opus 50.1301$47.6267.5M384k18h 51m2475
17Claude Sonnet 5.50.1301$50.58209.6M673k13h 41m40810
18Gemini 4 Argon0.1252$72.7447.3M391k5h 42m1646
19Claude Haiku 5.50.1246$11.47189.9M707k16h 52m4006
20Claude Haiku 5.50.1232$6.74107.0M520k13h 56m2931
21Muse Spark 1.30.1200$62.0457.0M274k16h 49m3293
22Gemini 3.8 Flash0.1144$3.3021.9M158k1h 16m1605
23Claude Haiku 5.50.1135$6.58101.1M551k18h 27m2774
24Muse Spark 1.30.1131$41.9045.4M252k18h 50m3047
25Grok 4.70.1109$12.5612.3M170k1h 49m852
26Kimi K30.1101$21.3546.7M229k17h 35m2826
27Grok 4.70.1098$130.86121.5M481k15h 47m4984
28Kimi K30.1097$26.9062.8M258k19h 1m3257
29Kimi K30.1091$18.2139.5M209k19h 3m2395
30Muse Spark 1.30.1082$55.0349.7M225k19h 54m3611
31Gemini 3.7 Flash0.1064$8.8840.2M172k5h 7m2652
32GLM-5.30.1050$34.1375.8M305k18h 42m3362
33Muse Spark 1.30.1039$52.8046.7M249k19h 50m3516
34GLM-5.30.1036$36.9494.3M365k18h 38m3593
35Gemini 3.8 Flash0.1027$5.1541.3M171k2h 11m2553
36Grok 4.60.1023$289.71280.9M1.3M20h 0m110991
37Grok 4.70.0968$55.0143.9M294k8h 31m1906
38Qwen3.8-Max-09020.0947$60.29210.7M1.0M19h 43m5751
39GLM-5.30.0941$44.44143.9M417k17h 20m4508
40Grok 4.70.0896$57.2942.5M256k5h 56m2036
41Qwen3.8-Max0.0879$12.0738.5M344k19h 44m2903
42Gemini 3.7 Flash0.0865$5.2520.8M119k3h 41m1721
43Gemini 3.7 Flash0.0846$10.2648.6M211k7h 0m2643
44GLM-5.3 Flash0.0784$2.7452.3M271k18h 56m2512
45Grok 4.60.0709$86.3377.3M437k10h 44m3176
46Qwen3.8-Max0.0652$23.1077.1M550k18h 46m4362
47Muse Spark 1.20.0557$16.8190.3M275k5h 28m3424
48Muse Spark 1.20.0507$33.64201.0M350k2h 20m4883
49Claude Opus 5.50.0000$41.05143.9M474k16h 43m41914
50Inkling0.0000$4.784.9M42k32m1361
51GLM-5.30.0000$28.5571.5M295k19h 12m3322
52Claude Sonnet 5.50.0000$60.75240.5M1.0M19h 26m5683
53Qwen3.8-Max-09020.0000$71.57251.7M1.2M18h 34m6263
54GLM-5.30.0000$43.34125.4M382k18h 56m4632
55Gemini 3.8 Flash0.0000$7.6244.2M197k3h 25m2414
56Claude Haiku 5.50.0000$7.52117.0M598k11h 15m2862
57GPT-5.6 Sol0.0000$29.4443.7M172k11h 11m2914
58Inkling0.0000$9.609.7M91k1h 37m1871
59Grok 4.70.0000$47.0135.3M253k6h 31m1694
60Qwen3.8-Max0.0000$18.8059.9M558k19h 4m3661
61DeepSeek V4 Flash Vision Exp0.0000$1.89103.3M298k19h 46m4353
62DeepSeek V4 Flash Vision Exp0.0000$2.64142.6M438k12h 9m4745
63Claude Sonnet 5.50.0000$49.78205.3M682k14h 7m4178
64Inkling0.0000$4.224.3M40k1h 20m1252
65GLM-5.3 Flash0.0000$5.34102.1M341k17h 52m4087
66Muse Spark 1.20.0000$8.1142.2M266k2h 10m1692
67Qwen3.8-Max0.0000$22.7775.2M580k19h 13m4923
68Qwen3.8-Max-09020.0000$64.31226.9M1.0M19h 20m6421
69GLM-5.3 Flash0.0000$2.8272.3M274k18h 58m3432
70Claude Haiku 5.50.0000$5.3979.0M529k13h 40m2153
71Grok 4.60.0000$51.2439.8M426k15h 47m2435
72Claude Opus 5.50.0000$25.8782.9M352k17h 21m2968
73GLM-5.3 Flash0.0000$2.3859.1M248k15h 20m3095
74Gemini 4 Argon0.0000$51.8259.1M521k9h 41m1785
75Gemini 3.8 Flash0.0000$7.4446.3M203k3h 16m2534
76Kimi K30.0000$18.6638.3M209k20h 0m2544
77DeepSeek V4 Flash Vision Exp0.0000$2.54140.9M373k17h 33m4735
78Qwen3.8-Max-09020.0000$63.28220.8M1.1M19h 41m5712
79Qwen3.8-Max0.0000$31.11106.6M635k17h 29m5003
80Inkling0.0000$9.219.4M67k2h 19m2351
81GPT-5.6 Sol0.0000$115.28137.3M233k11h 7m60310
82Kimi K30.0000$31.9877.8M334k19h 25m3394
83GLM-5.3 Flash0.0000$2.9554.2M261k17h 55m2723
84Claude Opus 50.0000$35.0347.7M304k18h 9m2067
85Qwen3.8-Max-09020.0000$57.59198.5M1.1M19h 22m5613
86DeepSeek V4 Flash Vision Exp0.0000$2.76151.1M447k15h 16m5036
87GPT-5.6 Sol0.0000$33.4341.9M177k7h 37m2574
88Gemini 3.7 Flash0.0000$6.9328.3M150k3h 32m2034
89Grok 4.60.0000$192.75185.2M1.2M14h 10m76664
90Claude Opus 50.0000$44.1362.7M352k17h 5m2435
91DeepSeek V4 Flash Vision Exp0.0000$2.75153.9M409k18h 4m5102
92Muse Spark 1.30.0000$54.2546.3M268k18h 59m3102
93Grok 4.60.0000$86.8176.6M468k16h 53m3369
94Gemini 3.7 Flash0.0000$15.5862.6M304k13h 22m2852
95Gemini 4 Argon0.0000$75.1654.4M420k6h 54m1856
96Muse Spark 1.20.0000$7.4939.5M207k4h 45m2182
97Gemini 3.8 Flash0.0000$9.5656.3M191k4h 7m3033
98Muse Spark 1.20.0000$9.6433.9M298k3h 46m1945
99Inkling0.0000$6.196.3M42k29m1201
100Claude Opus 5.50.0000$33.84113.6M428k17h 31m3469

Multi-GPU Efficient Finetuning

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Inkling0.5238$11.7812.1M59k1h 35m1661
2Claude Opus 5.50.4286$18.5551.6M316k17h 25m2014
3Muse Spark 1.20.3810$64.94126.7M662k16h 40m38627
4Claude Sonnet 5.50.3571$29.39111.1M559k18h 36m2642
5DeepSeek V4 Flash Vision Exp0.3333$0.8236.7M207k19h 58m2381
6Kimi K30.3333$19.1518.0M131k19h 9m1676
7Claude Opus 5.50.3333$13.0335.0M224k18h 31m1795
8Claude Opus 5.50.3095$18.4950.1M325k18h 23m1925
9Muse Spark 1.20.3095$11.9541.8M358k12h 44m19924
10Muse Spark 1.30.3095$25.5021.9M121k19h 28m1972
11Kimi K30.3095$16.5615.3M148k19h 10m1343
12Gemini 4 Argon0.3095$59.0860.8M237k16h 56m1985
13Claude Fable 50.2857$23.6614.1M128k18h 18m1192
14GLM-5.30.2857$12.8826.8M144k19h 0m2342
15Claude Fable 5.10.2857$5.657.6M75k17h 4m982
16Claude Opus 5.50.2857$21.9461.0M375k16h 29m2073
17Qwen3.8-Max0.2857$6.4217.1M316k18h 44m2135
18Claude Fable 5.10.2857$5.387.9M60k16h 16m1183
19Claude Haiku 5.50.2857$3.4948.9M402k16h 53m1633
20GLM-5.3 Flash0.2857$0.6810.0M99k15h 21m1243
21GLM-5.30.2857$10.4218.4M127k19h 10m1756
22Claude Opus 50.2857$20.6727.0M193k18h 45m1775
23Claude Haiku 5.50.2619$1.7824.5M255k17h 19m1352
24Claude Opus 5.50.2619$17.3345.0M317k18h 13m1784
25GLM-5.3 Flash0.2619$1.1715.8M143k16h 53m1343
26Claude Fable 50.2619$17.729.8M108k18h 5m1064
27Muse Spark 1.20.2619$355.312070.9M1.9M15h 46m592022
28GLM-5.3 Flash0.2619$0.9712.5M122k17h 37m1272
29Claude Sonnet 5.50.2619$34.13135.6M549k19h 19m3382
30Claude Fable 50.2619$30.0318.9M149k19h 3m1525
31Claude Fable 5.10.2619$6.128.6M75k18h 44m1124
32Qwen3.8-Max0.2619$6.1516.6M296k17h 38m22010
33Claude Opus 50.2381$22.4128.9M215k18h 43m1772
34GPT-5.6 Sol0.2381$19.3323.5M110k15h 47m1673
35Claude Fable 50.2381$19.0711.3M104k19h 17m1208
36GLM-5.3 Flash0.2381$1.3629.9M170k18h 53m2192
37Claude Opus 50.2381$21.9128.5M201k18h 44m1805
38Claude Fable 50.2381$17.669.8M106k18h 38m1066
39Claude Haiku 5.50.2143$2.4634.8M304k17h 30m1583
40Gemini 4 Argon0.2143$71.7765.5M249k18h 37m2008
41Claude Fable 5.10.2143$5.267.1M71k18h 19m923
42Gemini 3.8 Flash0.2143$4.9123.2M78k4h 58m1866
43GPT-6 Astra0.2143$155.5978.1M233k19h 27m2996
44Claude Opus 50.2143$16.3319.4M178k17h 33m1423
45Gemini 3.7 Flash0.2143$10.2429.6M72k9h 49m18131
46Claude Haiku 5.50.1905$3.2445.3M385k19h 9m1571
47GPT-6 Astra0.1905$229.70113.1M288k19h 53m3646
48Muse Spark 1.20.1905$5.5220.2M214k2h 15m1353
49Gemini 4 Argon0.1905$119.5980.8M260k19h 19m2303
50GPT-6 Astra0.1905$125.1064.1M212k19h 30m2616
51Kimi K30.1905$16.1311.8M128k18h 47m1161
52Gemini 3.7 Flash0.1667$11.8531.1M102k19h 53m20210
53Claude Sonnet 5.50.1667$34.90136.3M593k18h 28m3143
54Claude Sonnet 5.50.1667$37.45150.3M578k14h 47m3433
55Claude Fable 5.10.1667$6.929.6M88k17h 1m1014
56DeepSeek V4 Flash Vision Exp0.1429$0.9241.7M226k19h 50m2512
57Muse Spark 1.30.1429$16.1814.5M230k20h 0m1591
58Gemini 4 Argon0.1429$59.3568.3M219k18h 18m2077
59Gemini 4 Argon0.1190$99.1676.3M304k18h 34m2334
60Gemini 3.8 Flash0.0952$10.1937.4M109k8h 17m22711
61GPT-6 Astra0.0714$291.48141.3M320k19h 38m4026
62Claude Haiku 5.50.0714$4.8271.2M466k18h 3m2191
63GLM-5.30.0714$17.6133.2M221k18h 56m2112
64Qwen3.8-Max-09020.0476$21.6951.3M683k18h 46m3343
65Muse Spark 1.20.0476$35.64132.6M581k10h 53m45113
66Qwen3.8-Max-09020.0476$21.7463.3M874k19h 49m3973
67Kimi K30.0476$25.1335.1M233k19h 37m2361
68Inkling0.0476$5.355.5M24k1h 26m1322
69GPT-5.6 Sol0.0238$19.6525.0M71k12h 53m1333
70Inkling0.0238$14.2214.8M45k2h 19m2191
71DeepSeek V4 Flash Vision Exp0.0238$0.6629.1M168k19h 41m2262
72Grok 4.70.0000$60.2136.3M189k18h 34m1842
73Muse Spark 1.30.0000$22.9620.6M169k19h 58m1575
74Qwen3.8-Max0.0000$4.6511.0M287k19h 49m1835
75Gemini 3.7 Flash0.0000$22.1847.8M107k18h 31m2992
76Grok 4.70.0000$37.8924.1M164k18h 10m1402
77GPT-5.6 Sol0.0000$16.4525.9M78k16h 50m1802
78GLM-5.30.0000$20.2634.9M208k19h 31m2114
79Claude Opus 50.0000$20.7027.2M184k19h 13m1733
80Inkling0.0000$6.666.8M46k2h 1m1351
81GPT-5.6 Sol0.0000$24.1334.7M95k16h 10m1812
82GPT-5.6 Sol0.0000$30.4139.1M90k14h 8m1993
83Grok 4.60.0000$47.0350.4M373k19h 22m26113
84Qwen3.8-Max0.0000$3.679.9M171k19h 13m1533
85Qwen3.8-Max-09020.0000$6.948.9M369k5h 21m1201
86GLM-5.30.0000$17.6732.5M199k19h 29m2152
87Muse Spark 1.30.0000$12.9112.2M103k19h 52m1421
88DeepSeek V4 Flash Vision Exp0.0000$0.7637.0M151k19h 59m2751
89Gemini 3.8 Flash0.0000$11.9258.4M116k9h 56m3017
90Qwen3.8-Max0.0000$7.4421.5M284k19h 29m2532
91Grok 4.60.0000$18.5324.3M327k17h 14m1947
92DeepSeek V4 Flash Vision Exp0.0000$1.2360.8M248k19h 49m3231
93Qwen3.8-Max-09020.0000$21.7360.3M968k19h 32m3663
94Grok 4.60.0000$32.8828.8M249k18h 12m1965
95Muse Spark 1.30.0000$30.0827.4M216k19h 49m2041
96Gemini 3.7 Flash0.0000$8.3027.1M102k9h 38m18810
97GPT-6 Astra0.0000$142.9574.8M253k19h 46m3117
98Grok 4.60.0000$23.9518.0M271k19h 15m1454
99Inkling0.0000$4.164.3M15k34m1073
100Kimi K30.0000$10.948.7M101k18h 40m1211
101Gemini 3.8 Flash0.0000$9.4651.9M115k6h 1m2686
102Claude Sonnet 5.50.0000$32.34129.9M492k18h 23m3262
103Grok 4.70.0000$29.8818.4M159k14h 59m1193
104Gemini 3.7 Flash0.0000$30.3173.0M132k18h 49m31013
105GLM-5.3 Flash0.0000$2.3142.4M198k17h 43m2612
106Qwen3.8-Max-09020.0000$37.59115.3M1.0M19h 35m5413
107Grok 4.70.0000$36.1819.8M164k20h 0m1265
108Gemini 3.8 Flash0.0000$14.9862.0M118k8h 40m2957
109Grok 4.70.0000$59.6535.5M185k17h 44m1703
110Grok 4.60.0000$20.0718.4M217k18h 24m1568

Notebook Compression

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Sonnet 5.50.7077$121.38505.5M1.6M19h 29m114023
2Claude Opus 5.50.6404$76.14300.9M607k18h 32m62033
3Claude Opus 5.50.6166$96.89380.6M802k18h 37m87233
4GPT-6 Astra0.6122$2035.40958.4M1.9M17h 45m213253
5GPT-6 Astra0.6063$2124.531006.7M2.1M18h 49m230842
6Claude Sonnet 5.50.6038$113.09459.8M1.7M19h 12m103719
7Claude Fable 5.10.6002$67.85117.2M379k14h 26m40117
8Claude Sonnet 5.50.5947$105.86436.0M1.5M19h 24m9942
9Claude Sonnet 5.50.5930$98.59408.5M1.3M17h 41m8271
10Claude Opus 5.50.5926$80.88317.0M668k19h 35m60629
11Claude Fable 5.10.5736$77.68134.5M428k13h 49m45016
12Claude Sonnet 5.50.5678$87.19362.7M1.2M18h 49m8088
13Claude Opus 5.50.5584$79.55318.4M608k18h 25m64927
14Claude Opus 5.50.5566$69.33267.9M597k18h 1m55728
15Claude Fable 5.10.5457$68.00118.2M365k13h 15m41921
16GPT-6 Astra0.5422$1208.04578.6M1.3M19h 17m138924
17Claude Haiku 5.50.5323$15.39247.7M1.1M15h 23m6183
18Claude Fable 5.10.5279$64.70113.1M334k17h 24m41917
19Claude Opus 50.5259$112.64181.6M606k17h 57m45417
20Claude Haiku 5.50.5238$18.15307.8M1.1M18h 41m70723
21Claude Fable 50.4971$137.67106.8M434k17h 17m39015
22Claude Fable 50.4861$123.2190.8M455k18h 4m31816
23Claude Fable 5.10.4824$61.77107.1M338k15h 49m41816
24Gemini 4 Argon0.4592$350.30290.6M1.5M20h 36m69025
25Claude Opus 50.4532$73.01109.0M516k14h 40m35212
26Claude Haiku 5.50.4519$14.24235.9M949k18h 16m56121
27Gemini 4 Argon0.4467$232.09321.0M1.6M20h 40m70628
28Claude Opus 50.4439$118.20194.6M584k18h 55m50714
29Claude Opus 50.4351$112.61183.8M577k18h 34m47119
30GPT-6 Astra0.4322$274.97132.6M360k5h 47m4077
31Claude Opus 50.4296$84.72133.1M506k18h 0m38312
32Claude Haiku 5.50.4204$18.03295.9M1.2M15h 35m6887
33GPT-6 Astra0.4121$327.78158.4M411k6h 16m48210
34Gemini 4 Argon0.4112$223.42270.8M1.5M21h 0m63423
35Gemini 4 Argon0.3971$258.69226.7M1.1M20h 39m49816
36Gemini 4 Argon0.3901$194.88235.0M1.3M15h 31m56613
37Claude Fable 50.3654$123.5292.2M440k14h 28m33013
38Claude Fable 50.3578$103.7973.7M421k17h 44m27313
39Claude Haiku 5.50.3415$9.66154.9M685k7h 45m3279
40Claude Fable 50.3346$106.6778.6M394k17h 8m29315
41GLM-5.30.2770$25.8686.5M327k19h 49m3703
42GLM-5.30.2744$34.96116.4M391k19h 2m4352
43Muse Spark 1.30.2729$60.3265.3M317k6h 41m35711
44Kimi K30.2647$37.6696.4M363k19h 31m40917
45GPT-5.6 Sol0.2623$123.00167.4M279k11h 19m6288
46Qwen3.8-Max-09020.2600$30.2389.6M1.1M20h 1m3861
47GPT-5.6 Sol0.2599$99.01115.0M257k15h 3m52810
48Grok 4.70.2584$211.20205.8M904k13h 1m85913
49Qwen3.8-Max-09020.2513$27.9279.6M1.2M19h 13m4073
50Grok 4.70.2464$38.1737.7M250k3h 43m1928
51GPT-5.6 Sol0.2438$58.4876.1M190k17h 55m41214
52Grok 4.70.2422$40.6041.8M253k4h 6m22111
53Qwen3.8-Max-09020.2416$28.6981.5M1.3M19h 35m4231
54Kimi K30.2338$43.76111.9M405k17h 35m40312
55GPT-5.6 Sol0.2326$88.19110.8M211k11h 35m5186
56GLM-5.3 Flash0.2312$4.45118.7M338k13h 55m4773
57Grok 4.60.2286$85.3184.1M498k7h 48m33114
58Muse Spark 1.30.2285$27.0179.4M314k19h 7m4078
59Kimi K30.2242$36.2787.9M412k11h 52m38212
60GLM-5.3 Flash0.2231$4.83113.6M398k17h 19m45518
61Grok 4.70.2221$20.9623.3M213k3h 13m1495
62Qwen3.8-Max-09020.2219$31.2388.3M1.4M19h 46m4781
63Qwen3.8-Max0.2190$26.3283.3M818k19h 14m4542
64Qwen3.8-Max0.2153$10.8227.5M610k19h 5m3142
65Kimi K30.2151$24.4560.7M274k11h 45m30210
66Qwen3.8-Max-09020.2150$30.5585.1M1.4M19h 31m4033
67GLM-5.3 Flash0.2148$5.19105.1M375k18h 46m4102
68Grok 4.60.2146$36.9834.6M412k13h 20m2205
69DeepSeek V4 Flash Vision Exp0.2139$1.97101.8M387k13h 26m4201
70GLM-5.3 Flash0.2132$3.4459.6M295k17h 49m3002
71Qwen3.8-Max0.2125$16.1547.4M646k17h 46m3622
72Gemini 3.8 Flash0.2118$6.5547.0M149k3h 4m2866
73Muse Spark 1.30.2112$78.1476.4M260k11h 8m3583
74Grok 4.60.2098$96.3888.3M636k11h 39m37712
75GLM-5.30.2089$39.2889.8M362k20h 0m3691
76Grok 4.60.2060$71.5475.2M388k6h 34m38127
77GLM-5.30.2058$59.65209.0M565k15h 11m5488
78DeepSeek V4 Flash Vision Exp0.2028$2.58144.1M374k19h 46m5082
79Grok 4.60.2019$87.9283.6M470k8h 37m36110
80Grok 4.70.2015$41.0638.3M268k3h 17m1885
81Qwen3.8-Max0.2005$15.4343.7M693k18h 44m4141
82Kimi K30.1961$13.5921.1M194k9h 53m1799
83DeepSeek V4 Flash Vision Exp0.1948$3.01169.4M449k11h 0m5514
84DeepSeek V4 Flash Vision Exp0.1939$2.93164.0M435k14h 31m5264
85Gemini 3.8 Flash0.1896$6.3445.8M152k4h 56m3086
86Qwen3.8-Max0.1831$20.1858.6M851k19h 8m4432
87GLM-5.3 Flash0.1829$5.2490.6M377k19h 26m3522
88DeepSeek V4 Flash Vision Exp0.1818$2.40126.7M415k10h 56m4216
89Gemini 3.8 Flash0.1802$4.6334.5M148k3h 0m2256
90Gemini 3.7 Flash0.1775$2.9513.6M108k3h 17m1292
91Gemini 3.7 Flash0.1714$6.9227.7M160k6h 28m2365
92Muse Spark 1.20.1646$89.68227.7M1.2M20h 2m7287
93Gemini 3.8 Flash0.1634$11.1562.0M214k5h 27m3157
94GPT-5.6 Sol0.1417$64.2780.6M214k10h 2m3893
95Muse Spark 1.20.1353$32.24170.7M487k10h 37m5515
96Muse Spark 1.30.1309$65.0467.7M249k11h 11m3716
97GLM-5.30.1261$28.9386.9M409k13h 16m3282
98Muse Spark 1.30.1170$63.5077.9M313k5h 49m3263
99Muse Spark 1.20.0816$32.40192.3M534k7h 46m5704
100Gemini 3.7 Flash0.0417$2.9916.0M112k3h 8m1656
101Gemini 3.7 Flash0.0412$3.0519.8M150k3h 10m19410
102Gemini 3.7 Flash0.0403$4.5617.9M128k4h 20m1458
103Muse Spark 1.20.0387$183.05621.0M1.3M19h 7m14977
104Muse Spark 1.20.0356$37.95196.7M1.2M19h 2m6693
105Gemini 3.8 Flash0.0292$4.1023.6M91k4h 7m2255
106Inkling0.0214$5.305.4M31k3h 11m1842
107Inkling0.0209$6.766.9M44k2h 24m1932
108Inkling0.0205$8.128.4M30k3h 20m1851
109Inkling0.0203$5.445.6M27k1h 39m1213
110Inkling0.0179$5.866.0M36k2h 37m1662

Optimizer Design

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.3908$28.0787.7M400k17h 51m28612
2Gemini 4 Argon0.3700$138.1888.1M358k17h 59m2257
3GPT-6 Astra0.3513$198.61101.4M290k17h 55m3815
4GPT-5.6 Sol0.3487$65.5380.8M133k10h 22m4334
5Claude Sonnet 5.50.3328$24.9296.2M443k18h 17m3132
6Gemini 4 Argon0.3302$144.66126.0M552k18h 30m3276
7GPT-5.6 Sol0.3194$196.66203.2M202k11h 49m67823
8Kimi K30.3057$15.0637.2M181k19h 11m2754
9Grok 4.70.2867$182.37175.0M483k20h 0m74415
10GPT-5.6 Sol0.2846$55.2972.7M133k15h 42m4235
11Gemini 4 Argon0.2842$147.5293.7M408k17h 44m2466
12Claude Opus 5.50.2824$26.9882.6M395k14h 4m2826
13GPT-5.6 Sol0.2809$71.6593.2M177k14h 22m52321
14Gemini 4 Argon0.2729$106.8362.5M361k17h 2m2006
15Claude Opus 5.50.2715$26.8783.2M387k12h 26m2818
16Claude Sonnet 5.50.2671$40.11160.9M619k15h 53m3563
17Gemini 4 Argon0.2637$128.39105.4M394k12h 7m2616
18Claude Opus 5.50.2621$24.2868.6M403k13h 10m2304
19Claude Sonnet 5.50.2578$28.93110.0M545k14h 19m2822
20Grok 4.60.2557$99.1498.0M624k19h 20m42418
21GLM-5.3 Flash0.2521$2.9148.3M286k16h 23m2413
22Claude Opus 50.2499$36.8448.8M334k17h 28m2032
23Claude Fable 50.2478$59.8943.2M223k15h 59m22910
24Claude Sonnet 5.50.2467$39.74163.6M545k19h 1m3913
25GLM-5.30.2349$19.9835.0M224k17h 41m1923
26Qwen3.8-Max-09020.2342$15.3642.2M714k19h 22m3362
27Claude Fable 5.10.2272$15.4522.4M175k11h 13m1645
28GPT-5.6 Sol0.2234$31.2952.9M100k13h 17m3732
29GLM-5.30.2192$17.3736.9M195k19h 6m2412
30Claude Sonnet 5.50.2147$34.56138.5M535k18h 9m3652
31GLM-5.30.2082$16.4826.8M198k19h 23m1843
32GLM-5.3 Flash0.2047$1.3517.1M199k16h 48m1312
33Grok 4.70.2033$279.55260.9M639k20h 0m94917
34Grok 4.60.1957$53.9066.7M503k19h 24m39524
35Muse Spark 1.30.1949$17.6714.5M143k19h 59m1501
36GPT-6 Astra0.1940$334.17159.8M312k18h 23m4127
37Claude Haiku 5.50.1858$3.9658.4M400k17h 26m2172
38Qwen3.8-Max-09020.1854$14.0033.7M859k19h 56m3151
39GPT-6 Astra0.1777$89.9548.3M203k19h 38m24410
40Claude Opus 50.1760$28.5236.5M275k16h 52m1823
41Claude Fable 5.10.1750$17.1526.3M165k12h 46m1826
42Claude Opus 5.50.1731$23.2867.5M372k18h 2m2387
43Claude Opus 50.1714$43.9457.7M410k17h 5m2004
44Claude Haiku 5.50.1698$7.09114.6M506k14h 15m3253
45Grok 4.60.1570$59.5357.5M295k19h 26m25811
46Kimi K30.1475$41.51100.0M508k20h 1m3544
47Claude Fable 5.10.1459$14.9022.4M152k15h 9m1714
48Claude Haiku 5.50.1416$5.3082.3M440k13h 57m2561
49Kimi K30.1370$16.0538.0M228k19h 25m2224
50Grok 4.60.1368$54.4949.3M462k19h 16m24010
51Qwen3.8-Max-09020.1351$14.6142.4M583k19h 28m3341
52Claude Fable 5.10.1343$11.0815.3M141k13h 28m1343
53Claude Opus 50.1316$29.9237.9M299k16h 54m1792
54Gemini 3.7 Flash0.1194$22.13241.0M134k10h 36m8342
55Claude Fable 50.1170$54.5837.6M230k16h 38m2145
56Claude Haiku 5.50.1133$4.7675.7M379k15h 43m2631
57DeepSeek V4 Flash Vision Exp0.1123$1.1252.3M255k18h 23m2562
58Muse Spark 1.30.1110$29.2125.7M102k19h 53m3072
59Claude Haiku 5.50.1082$4.3564.8M433k15h 17m2312
60Muse Spark 1.30.1023$23.8020.6M126k19h 41m2602
61Kimi K30.0990$22.5849.0M297k17h 53m2416
62GLM-5.30.0984$17.0155.5M261k19h 4m2775
63GLM-5.30.0965$13.4723.0M159k18h 59m1802
64GLM-5.3 Flash0.0964$2.9336.3M234k16h 39m2233
65Qwen3.8-Max-09020.0958$20.9159.3M909k19h 56m3752
66GPT-6 Astra0.0929$278.29132.5M303k16h 52m3787
67Claude Fable 50.0927$57.4840.3M232k16h 57m2104
68GLM-5.3 Flash0.0879$2.6737.1M228k16h 58m2072
69Gemini 3.8 Flash0.0861$8.1432.5M139k6h 7m2202
70Gemini 3.8 Flash0.0851$12.8446.8M190k10h 59m2165
71Grok 4.60.0839$80.4575.7M333k19h 42m2793
72Qwen3.8-Max0.0827$7.6817.4M516k19h 49m2263
73DeepSeek V4 Flash Vision Exp0.0770$1.2263.5M222k19h 1m3342
74Gemini 3.8 Flash0.0755$12.8341.1M192k11h 46m2204
75Qwen3.8-Max0.0741$7.6118.8M448k19h 35m2413
76Claude Fable 50.0728$58.6940.0M246k15h 56m2039
77Qwen3.8-Max0.0655$6.8715.9M443k19h 59m2033
78Claude Fable 50.0619$49.5134.2M205k16h 37m1993
79Gemini 3.7 Flash0.0537$10.3785.1M122k13h 22m4352
80GPT-6 Astra0.0523$53.3535.6M191k19h 46m2186
81Gemini 3.8 Flash0.0506$9.3445.5M175k10h 6m2332
82Gemini 3.7 Flash0.0405$25.34217.9M182k10h 29m7442
83DeepSeek V4 Flash Vision Exp0.0348$1.4475.8M242k19h 19m3492
84GLM-5.3 Flash0.0292$1.9336.7M215k18h 0m2233
85Claude Fable 5.10.0226$15.7421.7M202k14h 5m1414
86Qwen3.8-Max0.0143$7.3218.3M421k19h 31m2381
87Grok 4.70.0119$55.6143.7M222k7h 51m1957
88Gemini 3.8 Flash0.0094$13.9975.0M146k11h 41m3845
89Grok 4.70.0000$308.24304.6M520k20h 0m12151
90Muse Spark 1.20.0000$39.2585.0M351k13h 51m2757
91Muse Spark 1.20.0000$46.70116.8M475k9h 50m3648
92DeepSeek V4 Flash Vision Exp0.0000$1.5179.4M262k19h 14m4062
93Muse Spark 1.20.0000$55.59163.2M672k19h 37m5671
94Gemini 3.7 Flash0.0000$28.88259.5M185k18h 35m9081
95Gemini 3.7 Flash0.0000$12.4147.0M144k13h 48m2972
96DeepSeek V4 Flash Vision Exp0.0000$1.3365.8M275k19h 51m3131
97Muse Spark 1.20.0000$27.0448.5M345k6h 22m2563
98Grok 4.70.0000$72.6566.7M251k9h 7m2659
99Muse Spark 1.30.0000$14.0411.9M125k19h 29m1791
100Muse Spark 1.20.0000$16.2119.8M148k19h 57m1881
101Inkling0.0000$1.081.1M14k1h 4m581
102Kimi K30.0000$19.0542.1M297k14h 45m2193
103Inkling0.0000$1.531.5M16k1h 13m732
104Qwen3.8-Max-09020.0000$24.4366.6M1.2M19h 37m3812
105Qwen3.8-Max0.0000$12.4233.0M636k19h 59m3031
106Inkling0.0000$3.843.9M25k5h 18m1241
107Muse Spark 1.30.0000$22.0318.0M123k19h 58m2012
108Inkling0.0000$2.542.6M28k2h 1m881
109Inkling0.0000$1.631.6M27k1h 46m731
110Claude Opus 50.0000$34.4342.6M358k17h 38m1733

PostgreSQL 18 on SQLite

task page →109 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.7308$2982.001383.4M2.9M19h 56m307367
2GPT-6 Astra0.7143$3132.521453.4M2.8M19h 51m314044
3Gemini 4 Argon0.6923$41.6362.6M389k2h 48m1922
4Gemini 4 Argon0.6923$43.9265.5M430k2h 31m1922
5Gemini 4 Argon0.6923$26.3282.0M301k2h 32m2242
6Gemini 4 Argon0.6923$25.4364.1M365k2h 39m1862
7GPT-6 Astra0.6593$3139.161477.1M2.8M19h 52m328073
8Gemini 4 Argon0.6484$34.6793.0M375k2h 50m2502
9GPT-6 Astra0.6484$3119.081452.8M2.8M19h 56m310862
10GPT-6 Astra0.6209$3312.101548.3M2.9M20h 0m325561
11Claude Opus 5.50.5934$433.391590.6M4.3M19h 2m364018
12Claude Opus 5.50.5659$363.101344.0M3.5M19h 34m317420
13Claude Sonnet 5.50.5549$310.171253.5M4.5M19h 16m292912
14GPT-5.6 Sol0.5275$209.42198.9M277k4h 5m58912
15Claude Sonnet 5.50.5000$308.881278.7M4.0M19h 11m28636
16Claude Sonnet 5.50.5000$284.211159.1M4.0M19h 17m27091
17Claude Sonnet 5.50.4780$247.761000.6M3.6M19h 38m23482
18Claude Opus 5.50.4615$283.281029.0M2.9M18h 59m231213
19Claude Sonnet 5.50.4451$309.321277.3M4.1M19h 4m29273
20Claude Fable 5.10.4011$588.091056.3M2.5M17h 46m251513
21Gemini 3.8 Flash0.4011$163.911747.0M1.9M19h 43m394186
22Claude Fable 5.10.3901$721.011319.3M2.5M17h 44m287214
23GPT-5.6 Sol0.3901$654.39640.1M687k19h 58m147228
24Gemini 3.8 Flash0.3846$244.902763.6M3.1M19h 16m6084124
25Claude Fable 5.10.3516$384.99680.6M1.8M18h 59m16889
26Claude Opus 50.3462$503.66880.6M1.6M19h 10m188312
27Claude Fable 50.3407$1287.661111.6M2.3M19h 25m250312
28Muse Spark 1.30.3407$551.80666.0M898k19h 58m17144
29Claude Fable 5.10.3352$475.86850.2M2.1M18h 4m18947
30Claude Opus 5.50.3352$189.85651.3M2.3M19h 20m14788
31Claude Opus 50.3352$381.03662.1M1.3M19h 37m14757
32Claude Opus 50.3352$353.77610.8M1.3M19h 43m12745
33Gemini 3.8 Flash0.3352$208.722281.9M3.1M19h 12m497191
34Gemini 3.8 Flash0.3297$180.311833.2M2.5M19h 54m4050100
35Claude Opus 50.3242$340.68578.1M1.3M19h 18m13326
36Claude Opus 5.50.2967$184.14630.5M2.2M19h 31m148710
37Claude Opus 50.2912$434.78748.3M1.6M18h 39m17745
38Claude Haiku 5.50.2857$70.441203.7M4.0M19h 19m265334
39Claude Haiku 5.50.2857$79.481383.8M3.8M17h 44m29005
40Grok 4.70.2747$697.58718.7M2.2M19h 51m297927
41Grok 4.70.2637$767.04780.4M2.4M18h 58m311730
42Claude Fable 50.2637$836.08698.8M1.8M19h 25m158013
43Claude Haiku 5.50.2637$80.981401.6M4.1M17h 22m30951
44Claude Fable 50.2637$945.64794.6M2.0M19h 56m17186
45Gemini 3.8 Flash0.2637$135.191385.8M1.8M16h 40m305361
46Gemini 3.7 Flash0.2582$124.971333.8M2.5M11h 51m301437
47Grok 4.70.2527$961.79986.1M3.0M20h 0m390926
48Gemini 3.7 Flash0.2418$144.251592.6M2.6M19h 46m345039
49Claude Fable 5.10.2308$392.90697.7M1.8M19h 16m16794
50Claude Haiku 5.50.2308$58.07999.5M3.0M18h 19m23206
51Gemini 3.7 Flash0.2253$193.892112.9M3.0M19h 55m468016
52Claude Haiku 5.50.2253$57.46996.8M2.8M17h 55m22753
53Grok 4.70.1978$1004.111036.8M3.4M20h 0m421722
54Gemini 3.7 Flash0.1758$159.991689.8M2.8M19h 49m375113
55Grok 4.60.1593$509.89496.5M1.6M19h 56m169670
56GLM-5.30.1593$191.86711.5M862k19h 53m174617
57Claude Fable 50.1538$641.49517.5M1.6M19h 39m12924
58Grok 4.60.1538$461.37465.7M1.9M17h 59m184249
59DeepSeek V4 Flash Vision Exp0.1484$22.501379.3M2.0M19h 53m31461
60GLM-5.30.1484$202.20744.7M1.0M19h 42m17897
61GLM-5.30.1374$201.89706.7M843k19h 32m15859
62GLM-5.30.1374$155.77570.5M772k19h 52m13842
63Qwen3.8-Max0.1374$186.86700.0M1.6M19h 30m18222
64Qwen3.8-Max0.1319$178.70667.7M1.7M19h 47m15494
65DeepSeek V4 Flash Vision Exp0.1264$22.611383.3M2.0M19h 51m32723
66Muse Spark 1.30.1099$305.431604.1M2.2M20h 0m36902
67DeepSeek V4 Flash Vision Exp0.1044$19.661214.6M1.7M19h 25m26889
68Grok 4.60.0989$257.56255.7M1.5M8h 44m95217
69GLM-5.30.0989$219.76822.5M966k19h 50m190311
70GLM-5.3 Flash0.0769$23.42737.2M1.0M19h 23m15784
71Qwen3.8-Max0.0769$170.86638.4M1.5M19h 53m15872
72Grok 4.60.0714$398.74383.4M2.7M19h 51m145734
73Kimi K30.0714$227.56673.8M1.2M20h 0m15281
74DeepSeek V4 Flash Vision Exp0.0659$23.231428.3M2.0M19h 44m33481
75Qwen3.8-Max0.0659$174.14653.5M1.5M19h 26m15361
76GLM-5.3 Flash0.0659$26.47848.3M1.3M18h 3m166311
77Kimi K30.0659$265.37772.2M1.4M20h 1m14271
78Kimi K30.0604$238.20702.8M1.4M20h 1m15131
79Muse Spark 1.30.0549$522.84598.7M1.2M20h 0m15251
80Muse Spark 1.30.0549$518.76603.9M1.1M19h 59m15721
81Qwen3.8-Max0.0549$158.21583.9M1.7M19h 23m14053
82Kimi K30.0495$197.52561.9M1.3M20h 0m11681
83GLM-5.3 Flash0.0495$25.01730.3M929k19h 49m17091
84Grok 4.60.0495$148.44141.0M985k6h 17m55910
85Gemini 3.7 Flash0.0495$17.96182.1M620k1h 34m4022
86Muse Spark 1.30.0495$525.95562.0M986k20h 0m13871
87Qwen3.8-Max-09020.0330$183.61654.3M2.6M19h 34m17372
88GLM-5.3 Flash0.0330$27.79699.2M1.1M19h 38m149610
89Qwen3.8-Max-09020.0330$116.07407.7M1.9M20h 1m11222
90Qwen3.8-Max-09020.0220$150.66544.1M1.9M20h 0m14341
91GLM-5.3 Flash0.0220$24.50755.8M998k19h 51m189914
92Qwen3.8-Max-09020.0165$112.13383.6M1.8M19h 52m11325
93DeepSeek V4 Flash Vision Exp0.0165$8.18489.5M856k20h 0m11942
94Qwen3.8-Max-09020.0110$104.91366.4M1.7M20h 1m10931
95Muse Spark 1.20.0055$37.82217.7M976k3h 48m49610
96Muse Spark 1.20.0055$40.72146.5M561k3h 14m4204
97GPT-5.6 Sol0.0055†$293.05285.8M311k4h 20m6716
98Muse Spark 1.20.0000$32.40176.5M473k2h 53m4363
99Inkling0.0000$22.3423.3M56k1h 53m3403
100Claude Fable 50.0000†$385.63316.2M920k5h 26m7383
101Muse Spark 1.20.0000$14.0883.6M240k1h 8m3142
102GPT-5.6 Sol0.0000$137.59141.5M243k3h 27m4802
103GPT-5.6 Sol0.0000$142.29142.1M259k4h 34m46211
104Grok 4.70.0000$890.38903.6M3.1M20h 0m366012
105Inkling0.0000$19.0619.8M53k1h 41m3022
106Inkling0.0000$19.0419.9M46k23m2521
107Inkling0.0000$16.5617.2M48k32m2142
108Inkling0.0000$16.6217.3M42k34m2871
109Muse Spark 1.20.0000$33.19162.4M603k2h 4m4581

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Quantum ESPRESSO pw.x in Rust

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9756$115.01354.9M1.7M9h 7m78413
2Claude Sonnet 5.50.9756$170.72658.9M3.1M17h 11m143815
3Claude Opus 5.50.9756$120.52382.4M1.7M11h 39m86725
4Claude Opus 5.50.9594$109.78339.6M1.6M7h 33m78612
5Claude Opus 5.50.9512$58.52152.7M1.1M4h 44m3506
6Claude Sonnet 5.50.9512$124.72468.1M2.5M11h 1m10545
7Claude Fable 5.10.9431$100.68158.8M876k5h 35m40811
8Claude Sonnet 5.50.9431$92.52348.6M1.8M7h 56m74815
9Claude Sonnet 5.50.9431$139.31539.0M2.5M15h 11m114112
10GPT-6 Astra0.9350$571.91270.6M494k3h 53m5704
11Claude Opus 5.50.9350$70.36204.4M1.1M5h 26m46011
12Claude Fable 5.10.9350$63.8099.1M584k3h 4m2188
13Claude Sonnet 5.50.9350$154.31585.2M2.9M17h 40m129515
14GPT-6 Astra0.9350$540.43256.4M446k3h 37m5444
15Claude Fable 5.10.9268$63.9599.7M578k3h 23m2225
16Claude Fable 5.10.9187$72.59116.9M580k4h 7m2455
17Gemini 4 Argon0.9187$119.37259.0M1.1M10h 5m6451
18Gemini 4 Argon0.9106$303.04318.6M1.2M11h 58m6912
19Claude Fable 5.10.9106$77.90124.4M643k3h 55m2564
20Gemini 4 Argon0.9024$154.81373.7M1.6M12h 47m8872
21Gemini 4 Argon0.9024$388.42369.1M1.6M13h 39m8676
22Gemini 4 Argon0.8699$138.25365.2M1.5M10h 38m8562
23GPT-6 Astra0.8699$378.55179.5M449k3h 11m4595
24Claude Fable 50.8699$390.43293.5M1.3M11h 49m65610
25GPT-6 Astra0.8699$279.05132.3M363k2h 37m3724
26Claude Fable 50.8618$392.73295.7M1.3M10h 46m6589
27GPT-6 Astra0.8293$299.55142.9M339k2h 28m4024
28Claude Opus 50.8211$159.35224.3M1.3M7h 45m5137
29Claude Fable 50.8211$384.44289.9M1.3M12h 52m6605
30Claude Opus 50.8211$245.12359.5M1.8M15h 10m82619
31Claude Opus 50.8130$286.81434.1M1.9M15h 11m97012
32Claude Opus 50.8130$184.58276.3M1.3M15h 20m6207
33Claude Fable 50.8049$335.99247.3M1.2M10h 59m5817
34Claude Fable 50.7967$346.56252.2M1.3M13h 4m6029
35Claude Haiku 5.50.7886$28.18430.1M2.5M14h 14m9678
36Claude Opus 50.7886$115.90152.7M1.1M6h 12m3908
37Claude Haiku 5.50.7724$22.74342.2M2.1M12h 39m7205
38Claude Haiku 5.50.7073$23.96363.4M2.1M14h 34m7753
39Claude Haiku 5.50.6341$29.37441.9M2.7M11h 2m9438
40Grok 4.70.6179$248.05251.2M1.1M11h 32m108616
41Claude Haiku 5.50.6179$20.61295.8M2.1M11h 25m6427
42GPT-5.6 Sol0.5203$304.21296.3M260k4h 50m6069
43GPT-5.6 Sol0.4634$57.4264.9M189k2h 47m27913
44Grok 4.70.4553$566.99570.1M2.1M20h 0m22811
45Gemini 3.8 Flash0.4553$73.38570.9M924k15h 34m14364
46GPT-5.6 Sol0.4553$120.99116.9M214k5h 5m4048
47Gemini 3.8 Flash0.4390$64.68501.7M861k10h 34m12292
48Muse Spark 1.30.4228$418.71442.8M1.1M20h 0m11191
49Muse Spark 1.30.4228$514.22583.5M1.3M19h 59m14151
50GPT-5.6 Sol0.4065$104.97107.5M204k3h 16m39110
51Grok 4.60.3984$196.95181.0M1.6M13h 51m68114
52Gemini 3.8 Flash0.3577$44.62399.0M781k9h 40m9797
53Muse Spark 1.30.3577$352.28387.2M1.4M19h 43m11533
54Grok 4.60.3008$282.67273.1M1.6M13h 49m97640
55Grok 4.70.2764$412.96420.2M1.8M14h 39m177917
56Grok 4.60.2683$1211.081191.6M2.2M19h 59m3559243
57Kimi K30.2602$75.00147.3M1.2M19h 51m4281
58GLM-5.30.1707$145.94507.1M1.3M19h 30m108213
59Gemini 3.7 Flash0.1545$46.71314.3M747k10h 28m7402
60Muse Spark 1.30.1463$336.34348.3M1.1M19h 35m9399
61GLM-5.30.1382$132.96476.8M1.3M19h 42m98412
62GLM-5.30.1301$108.12382.4M1.3M19h 32m8382
63Gemini 3.8 Flash0.1301$76.16654.7M1.0M15h 23m16946
64Grok 4.70.1138$593.38588.6M2.1M20h 0m23761
65Grok 4.60.1057$123.16111.5M1.7M10h 28m42913
66Gemini 3.8 Flash0.1057$39.41364.3M690k7h 35m8684
67Grok 4.60.0976$96.1488.3M1.1M7h 19m36012
68Gemini 3.7 Flash0.0976$71.79423.8M777k17h 50m9483
69Grok 4.70.0650$449.65416.6M1.1M20h 0m151711
70Gemini 3.7 Flash0.0650$36.49288.8M712k6h 10m7252
71GLM-5.30.0650$123.53403.7M1.6M19h 19m95711
72GLM-5.3 Flash0.0569$14.19350.7M1.3M17h 49m7933
73Kimi K30.0488$160.13415.5M1.7M20h 0m9991
74Muse Spark 1.20.0244$48.27287.1M1.0M3h 0m5981
75Kimi K30.0244$100.42211.3M1.8M20h 0m5661
76Muse Spark 1.30.0163$435.17464.8M1.2M19h 59m11961
77Kimi K30.0081$131.87355.0M1.3M19h 56m7856
78GLM-5.3 Flash0.0081$17.03435.1M1.2M17h 59m106516
79Qwen3.8-Max0.0000$48.53146.5M1.8M19h 49m4311
80Qwen3.8-Max-09020.0000$27.8947.8M2.0M20h 3m2361
81DeepSeek V4 Flash Vision Exp0.0000$7.62422.1M1.1M12h 5m9126
82Gemini 3.7 Flash0.0000$51.00393.0M804k11h 3m10024
83Kimi K30.0000$72.76158.2M1.2M20h 1m4181
84Muse Spark 1.20.0000$22.0858.0M685k1h 30m1943
85Qwen3.8-Max0.0000$54.35159.6M2.3M19h 59m4131
86Qwen3.8-Max0.0000$33.3786.6M1.8M19h 52m3012
87GLM-5.3 Flash0.0000$10.99299.0M1.2M12h 18m7135
88Gemini 3.7 Flash0.0000$24.96238.1M690k3h 15m5392
89GLM-5.3 Flash0.0000$9.30218.2M1.0M15h 25m6004
90Inkling0.0000$18.6819.4M66k28m1862
91DeepSeek V4 Flash Vision Exp0.0000$6.14336.4M959k16h 29m85310
92Qwen3.8-Max-09020.0000$30.5239.7M2.0M20h 1m1941
93Inkling0.0000$22.9424.0M46k17m2741
94DeepSeek V4 Flash Vision Exp0.0000$4.17227.6M660k6h 35m4473
95GPT-5.6 Sol0.0000$210.32203.5M250k6h 57m5776
96Inkling0.0000$8.198.5M35k16m1421
97Muse Spark 1.20.0000$8.0039.5M393k1h 21m1662
98Qwen3.8-Max-09020.0000$26.4847.3M2.3M20h 5m2311
99Inkling0.0000$9.259.5M49k17m1462
100Qwen3.8-Max-09020.0000$32.8967.0M2.0M20h 5m2851
101DeepSeek V4 Flash Vision Exp0.0000$6.64359.4M1.1M12h 22m8825
102GLM-5.30.0000$103.68348.9M1.2M19h 23m79514
103GLM-5.3 Flash0.0000$7.12187.9M1.1M14h 19m5624
104DeepSeek V4 Flash Vision Exp0.0000$6.97389.0M1.0M14h 29m8875
105Muse Spark 1.20.0000$5.4530.5M131k29m1603
106Qwen3.8-Max0.0000$35.4395.7M1.8M20h 1m3381
107Inkling0.0000$9.329.6M44k15m1382
108Muse Spark 1.20.0000$10.3054.9M392k1h 20m2484
109Qwen3.8-Max-09020.0000$26.3038.4M2.1M20h 8m2221
110Qwen3.8-Max0.0000$11.6213.4M1.3M19h 53m1121

Qubit Routing

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9241$44.40160.3M462k12h 19m4083
2Claude Opus 5.50.9229$49.89183.1M502k16h 23m42710
3GPT-6 Astra0.9207$412.86201.8M473k7h 46m59512
4GPT-6 Astra0.9186$1381.68662.3M1.4M17h 52m162126
5GPT-6 Astra0.9168$2130.531024.2M1.9M19h 50m238445
6Claude Opus 5.50.9138$40.04137.9M476k14h 14m37413
7Claude Sonnet 5.50.9132$39.23158.7M579k6h 58m35215
8GPT-6 Astra0.9131$2239.251067.1M2.1M19h 57m242954
9Claude Opus 5.50.9052$63.24243.8M546k14h 55m52821
10Claude Sonnet 5.50.9031$82.69337.6M1.2M18h 35m7611
11Claude Sonnet 5.50.9003$69.19287.2M925k18h 59m67110
12Claude Sonnet 5.50.8951$50.53209.6M671k12h 55m4127
13Claude Sonnet 5.50.8940$63.68259.4M928k17h 26m6354
14Claude Opus 50.8917$57.7085.6M405k15h 40m2776
15Claude Fable 5.10.8857$37.5960.9M295k9h 18m2396
16Claude Opus 50.8845$64.5299.6M401k17h 6m3133
17GPT-6 Astra0.8800$604.79292.5M576k8h 29m71511
18Claude Opus 5.50.8783$46.14171.7M451k17h 18m4479
19Claude Fable 5.10.8752$40.6567.2M290k7h 39m2749
20Claude Haiku 5.50.8732$11.20186.6M660k13h 13m3981
21Claude Fable 5.10.8680$40.9467.5M295k10h 23m2799
22Claude Opus 50.8644$47.7871.9M322k17h 28m2826
23Gemini 4 Argon0.8617$30.0862.2M527k4h 53m1764
24Claude Fable 5.10.8599$41.2367.7M303k9h 29m2569
25Claude Haiku 5.50.8544$5.8188.2M507k6h 15m2523
26Claude Fable 50.8542$114.2086.2M385k16h 7m28816
27Claude Fable 5.10.8541$59.53101.1M368k11h 5m3537
28Claude Opus 50.8538$47.8168.4M372k17h 11m2477
29Claude Haiku 5.50.8532$8.21132.2M569k9h 50m3132
30Gemini 4 Argon0.8488$43.6267.5M441k6h 4m1945
31Claude Opus 50.8444$51.0676.5M351k16h 37m2683
32Claude Fable 50.8371$94.8769.6M350k17h 59m2747
33Claude Haiku 5.50.8214$7.68123.8M539k9h 29m3172
34Gemini 4 Argon0.8155$105.2973.3M505k9h 43m1778
35Gemini 4 Argon0.7986$85.4056.4M543k6h 53m1504
36Claude Haiku 5.50.7982$10.12165.9M636k11h 29m3543
37Gemini 4 Argon0.7982$74.0164.4M466k6h 51m1817
38Claude Fable 50.7952$83.8460.4M319k16h 2m2379
39GPT-5.6 Sol0.7946$58.7777.9M203k6h 45m4238
40Qwen3.8-Max-09020.7845$41.21136.5M995k20h 0m4802
41GPT-5.6 Sol0.7781$75.1186.9M202k10h 41m41011
42Claude Fable 50.7664$98.6072.9M355k17h 31m2719
43Qwen3.8-Max-09020.7658$47.17161.4M937k19h 56m5311
44Claude Fable 50.7638$95.3170.8M336k16h 17m2657
45Gemini 3.7 Flash0.7591$2.339.2M139k1h 43m992
46GLM-5.30.7535$23.4664.7M277k19h 3m2676
47Kimi K30.7526$40.44107.3M401k19h 37m38717
48Grok 4.60.7350$123.13116.9M502k9h 53m41428
49Grok 4.70.7346$28.6227.0M233k2h 28m1197
50GLM-5.30.7343$45.4890.2M303k16h 27m3654
51GPT-5.6 Sol0.7314$114.07131.6M228k8h 56m56914
52Qwen3.8-Max-09020.7203$52.67179.1M1.1M19h 2m5202
53GPT-5.6 Sol0.7190$154.11169.8M283k6h 40m68813
54Kimi K30.7151$55.15146.5M497k20h 0m48414
55GPT-5.6 Sol0.7125$69.3392.1M185k8h 7m4755
56GLM-5.3 Flash0.7029$6.19134.2M441k12h 1m3873
57Kimi K30.6987$79.07224.2M641k20h 1m55612
58GLM-5.3 Flash0.6977$3.7863.8M292k10h 53m2735
59GLM-5.3 Flash0.6919$5.75129.8M427k15h 0m3614
60Qwen3.8-Max-09020.6915$35.54115.2M955k20h 1m4441
61GLM-5.30.6907$44.40135.6M383k15h 8m39212
62Gemini 3.8 Flash0.6886$9.1661.0M246k3h 25m2678
63Grok 4.60.6883$68.0360.3M544k3h 28m2496
64Qwen3.8-Max0.6875$16.9452.6M563k18h 44m3402
65Grok 4.70.6849$35.2935.5M255k1h 35m15710
66Muse Spark 1.30.6821$28.9785.7M430k5h 33m39621
67Muse Spark 1.30.6752$165.04162.2M432k18h 15m70625
68Gemini 3.8 Flash0.6750$4.9625.6M195k1h 47m1725
69Grok 4.70.6735$227.27226.0M738k19h 38m92575
70Grok 4.60.6689$82.9075.9M477k3h 6m28317
71Gemini 3.7 Flash0.6672$3.0415.3M126k1h 37m1401
72Grok 4.60.6619$46.4748.9M429k4h 33m2747
73Grok 4.70.6585$21.7722.6M209k1h 19m1227
74Muse Spark 1.30.6538$51.5157.6M507k5h 41m28610
75Gemini 3.7 Flash0.6446$3.4416.9M214k2h 28m1512
76Grok 4.70.6417$24.0124.2M210k1h 51m1314
77Qwen3.8-Max-09020.6374$51.28174.8M1.1M20h 1m5682
78GLM-5.30.6370$18.5955.0M231k19h 13m2873
79Kimi K30.6270$30.7976.7M394k12h 20m31820
80Kimi K30.6254$97.66258.3M819k19h 58m57617
81Muse Spark 1.30.6245$65.1569.0M497k6h 34m38113
82DeepSeek V4 Flash Vision Exp0.6244$2.53133.2M457k10h 50m4027
83Muse Spark 1.30.6205$141.97139.6M348k19h 5m58013
84Gemini 3.8 Flash0.6169$10.8884.0M323k4h 38m3002
85Muse Spark 1.20.6114$9.2347.6M407k3h 16m2624
86Gemini 3.7 Flash0.6074$16.2672.9M429k6h 43m2805
87GLM-5.30.6071$32.20106.0M372k12h 23m3755
88Gemini 3.8 Flash0.6021$4.9834.7M202k2h 25m2184
89Muse Spark 1.20.5947$9.3645.3M339k3h 54m2442
90Gemini 3.8 Flash0.5930$6.2047.0M194k4h 21m2244
91Grok 4.60.5924$84.0182.0M496k4h 20m33610
92Muse Spark 1.20.5914$9.2141.8M337k3h 53m2302
93Gemini 3.7 Flash0.5912$5.6344.5M188k5h 26m2701
94Muse Spark 1.20.5787$10.6452.8M389k2h 30m2728
95Qwen3.8-Max0.5728$25.9085.8M648k18h 2m4426
96GLM-5.3 Flash0.5673$4.2081.9M369k16h 1m3272
97Muse Spark 1.20.5545$7.7042.7M226k2h 46m2575
98DeepSeek V4 Flash Vision Exp0.5485$2.27120.4M400k9h 24m4053
99DeepSeek V4 Flash Vision Exp0.4883$3.26177.3M519k9h 8m4267
100DeepSeek V4 Flash Vision Exp0.4768$2.33127.1M362k12h 24m4074
101GLM-5.3 Flash0.4693$5.24113.1M401k10h 10m3619
102Qwen3.8-Max0.4459$25.1978.5M819k19h 40m3742
103DeepSeek V4 Flash Vision Exp0.4348$2.35127.0M382k9h 0m3957
104Inkling0.4268$4.274.3M39k1h 28m1012
105Qwen3.8-Max0.4074$19.9763.7M596k17h 56m3902
106Qwen3.8-Max0.2765$43.05138.5M1.3M20h 1m5121
107Inkling0.2712$3.613.7M31k1h 49m902
108Inkling0.2062$7.667.9M44k1h 46m1582
109Inkling0.1413$4.714.8M39k39m982
110Inkling0.0057$3.813.8M60k1h 38m951

Reconnaissance Blind Chess Recovery

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9929$30.52100.2M393k11h 17m2726
2Claude Sonnet 5.50.9857$55.39234.7M652k13h 43m4374
3GPT-6 Astra0.9857$244.69120.7M324k13h 51m40810
4Claude Opus 5.50.9786$45.44160.9M500k13h 11m37711
5Claude Opus 5.50.9786$34.33116.2M417k11h 0m3188
6Claude Sonnet 5.50.9750$40.76168.9M538k13h 54m3747
7Claude Opus 5.50.9750$38.61139.5M396k12h 25m3736
8Claude Sonnet 5.50.9643$41.04170.2M534k12h 48m3512
9Claude Opus 5.50.9571$39.47142.7M408k13h 40m3817
10Claude Fable 5.10.9536$56.7098.3M311k9h 23m3147
11Claude Sonnet 5.50.9536$50.70214.9M589k14h 7m4255
12Claude Fable 5.10.9536$46.0878.9M273k10h 59m2769
13Claude Fable 50.9500$67.0643.5M324k14h 13m1753
14Claude Sonnet 5.50.9464$44.69183.2M625k13h 17m3613
15Claude Opus 50.9429$45.4565.6M338k12h 24m2213
16Claude Fable 5.10.9429$31.3851.1M239k11h 53m2336
17GPT-6 Astra0.9429$571.36274.8M479k10h 52m6377
18Claude Fable 50.9357$59.5039.9M266k13h 11m1816
19Gemini 4 Argon0.9286$102.1388.3M440k7h 8m2247
20Gemini 4 Argon0.9214$93.51158.0M759k9h 17m42613
21Gemini 4 Argon0.8964$116.54131.7M765k9h 49m3738
22Gemini 4 Argon0.8893$85.6194.9M445k9h 1m1996
23GPT-5.6 Sol0.8893$28.4245.1M149k6h 33m2917
24Claude Fable 50.8821$103.7280.8M300k11h 27m2776
25Claude Opus 50.8750$46.2765.7M362k13h 32m2225
26Gemini 4 Argon0.8679$74.4368.7M419k7h 35m1924
27GPT-5.6 Sol0.8607$35.9957.3M138k6h 13m33613
28Grok 4.70.8571$107.3195.1M427k11h 56m40026
29Claude Opus 50.8500$61.1894.0M386k14h 7m2944
30Claude Opus 50.8429$60.2991.4M395k14h 7m2527
31GPT-6 Astra0.8429$330.64163.8M407k12h 13m5269
32Claude Fable 5.10.8357$41.8471.9M245k9h 32m25211
33GPT-6 Astra0.8357$771.41367.5M716k14h 57m90312
34Claude Haiku 5.50.8071$9.96166.2M583k11h 28m3426
35GPT-5.6 Sol0.8071$20.6232.5M99k10h 50m19610
36GPT-5.6 Sol0.8000$20.5330.5M123k2h 52m1973
37Claude Fable 5.10.7929$38.2264.0M257k7h 37m2454
38Grok 4.70.7821$110.9186.8M288k10h 45m30621
39Claude Opus 50.7643$37.8152.1M323k13h 43m2134
40Claude Fable 50.7607$96.2969.5M362k13h 19m2267
41Kimi K30.7571$29.2377.1M277k14h 20m3142
42GPT-6 Astra0.7536$12.034.8M92k34m693
43GPT-5.6 Sol0.7357$15.5121.1M106k11h 38m1689
44Grok 4.70.7250$43.2641.6M230k3h 58m1883
45Claude Haiku 5.50.6857$6.75107.9M485k12h 11m2734
46Claude Fable 50.6750$77.8654.6M319k13h 7m2144
47Claude Haiku 5.50.6321$6.72103.6M558k12h 23m2364
48Grok 4.60.6036$87.2970.2M604k8h 33m2599
49Grok 4.70.5893$172.69157.2M497k15h 0m62713
50Grok 4.60.5857$104.5199.3M819k14h 17m45324
51Grok 4.70.5607$45.1844.4M217k3h 31m1978
52Gemini 3.8 Flash0.5536$30.25260.8M509k6h 38m6143
53GLM-5.30.5357$48.03138.0M410k14h 33m3889
54GLM-5.3 Flash0.5250$5.0480.8M333k14h 2m2842
55Kimi K30.5071$31.5182.4M325k14h 46m3114
56Gemini 3.8 Flash0.4714$27.99242.3M700k9h 7m6696
57Muse Spark 1.30.4500$83.30135.3M1.0M14h 48m4594
58Gemini 3.8 Flash0.4500$19.92177.3M430k4h 7m4783
59Kimi K30.4286$27.4364.3M286k14h 50m25611
60Gemini 3.7 Flash0.4250$12.0951.0M293k4h 11m2663
61GLM-5.30.4214$29.5279.9M302k14h 26m3056
62Grok 4.60.4071$107.3799.7M852k13h 36m44317
63Muse Spark 1.20.4036$5.4124.7M331k4h 44m1502
64Muse Spark 1.20.4036$6.7330.6M391k4h 23m1324
65Muse Spark 1.20.3750$11.1857.5M431k6h 54m2546
66GLM-5.30.3607$36.0573.5M339k13h 30m2594
67Claude Haiku 5.50.3571$5.0075.9M441k13h 8m2223
68Muse Spark 1.20.3429$9.0140.4M451k7h 47m1974
69Claude Haiku 5.50.3357$5.6487.4M456k13h 10m2402
70Kimi K30.3143$28.9169.9M341k12h 50m2532
71Gemini 3.8 Flash0.3107$28.23250.7M518k4h 50m5514
72Gemini 3.7 Flash0.3000$23.11214.3M578k5h 22m5241
73GLM-5.30.2893$25.2683.8M284k14h 38m3394
74Grok 4.60.2786$78.3465.1M979k10h 29m3018
75GLM-5.30.2571$27.0269.8M315k14h 43m2536
76Gemini 3.7 Flash0.2393$20.54111.4M562k4h 43m3271
77Qwen3.8-Max-09020.2321$22.1036.7M1.2M15h 6m2391
78GLM-5.3 Flash0.2214$3.7065.2M342k14h 4m2502
79Muse Spark 1.20.2071$9.6939.5M748k4h 22m1387
80Inkling0.2000$1.231.2M15k1h 37m461
81DeepSeek V4 Flash Vision Exp0.1786$2.02107.0M337k14h 34m3282
82Kimi K30.1429$43.61116.1M397k14h 40m3952
83Qwen3.8-Max0.1357$20.2059.6M794k13h 51m3453
84Gemini 3.8 Flash0.1214$31.55253.4M764k12h 9m7342
85DeepSeek V4 Flash Vision Exp0.1214$2.99164.7M448k8h 44m4235
86GLM-5.3 Flash0.1214$5.5297.5M412k13h 40m3139
87Muse Spark 1.30.1107$38.26178.6M566k18h 5m65436
88Grok 4.60.0929$172.71159.1M1.1M14h 32m60914
89Qwen3.8-Max-09020.0929$21.3436.0M1.2M15h 8m2631
90Inkling0.0786$1.371.4M14k43m621
91Qwen3.8-Max0.0750$16.7049.8M638k13h 27m3353
92Qwen3.8-Max-09020.0607$20.0344.0M1.0M15h 2m2561
93Qwen3.8-Max0.0536$12.9235.1M623k13h 47m2383
94Gemini 3.7 Flash0.0536$30.51186.7M1.3M5h 45m5132
95Qwen3.8-Max0.0536$22.7970.5M780k13h 7m4153
96GLM-5.3 Flash0.0500$3.9472.4M357k14h 22m2512
97Gemini 3.7 Flash0.0429$30.88192.0M568k8h 45m5062
98Qwen3.8-Max-09020.0429$15.2334.3M1.0M15h 2m2201
99Inkling0.0393$5.275.4M45k1h 49m1272
100DeepSeek V4 Flash Vision Exp0.0357$2.71145.6M448k14h 17m3777
101Muse Spark 1.30.0286$195.94191.4M452k19h 7m6847
102GLM-5.3 Flash0.0179$4.71110.5M429k14h 10m3307
103DeepSeek V4 Flash Vision Exp0.0143$2.49130.6M440k11h 4m40010
104Inkling0.0143$2.102.1M21k28m831
105Qwen3.8-Max-09020.0143$12.3021.2M813k15h 8m1881
106Muse Spark 1.30.0107$34.91148.6M508k14h 14m57715
107Qwen3.8-Max0.0071$26.0582.8M805k13h 22m4363
108DeepSeek V4 Flash Vision Exp0.0036$2.74145.9M463k9h 28m3726
109Muse Spark 1.30.0036$74.56160.5M728k11h 20m62810
110Inkling0.0000$3.914.0M36k2h 12m982

SGLang Inference System Optimization

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.5349$1954.03921.6M1.6M19h 56m193231
2Gemini 4 Argon0.4359$139.21309.9M955k8h 57m7466
3Claude Sonnet 5.50.3720$144.95566.2M2.4M18h 50m134311
4Claude Haiku 5.50.1173$15.92254.5M1.2M10h 40m6252
5Muse Spark 1.30.1159$180.28204.8M347k10h 27m67014
6GPT-5.6 Sol0.1092$291.23284.1M251k5h 12m61612
7GPT-5.6 Sol0.0675$443.00437.3M281k6h 23m87714
8Grok 4.70.0552$802.99801.5M2.3M19h 22m318324
9GLM-5.30.0534$68.77241.2M448k15h 36m6508
10Muse Spark 1.20.0532$132.47498.4M1.4M17h 13m14443
11Claude Fable 50.0442$246.50205.1M519k8h 17m48110
12Grok 4.60.0322$488.14454.2M2.3M19h 33m170383
13Claude Opus 50.0249$124.87207.2M534k12h 23m4607
14Qwen3.8-Max-09020.0242$30.1991.7M767k20h 6m4341
15Claude Opus 50.0223$101.43161.0M523k12h 35m3908
16Qwen3.8-Max0.0214$45.80153.5M1.1M15h 59m7157
17GLM-5.30.0211$67.37244.9M383k14h 17m69820
18Gemini 3.8 Flash0.0190$30.46330.6M252k3h 24m70911
19Gemini 3.7 Flash0.0169$19.15195.9M289k3h 33m5054
20GPT-5.6 Sol0.0168$283.36279.0M247k6h 47m65521
21Kimi K30.0103$110.14311.1M507k20h 1m74011
22Muse Spark 1.20.0099$100.58403.5M1.7M11h 46m11938
23Muse Spark 1.20.0081$15.0390.2M152k1h 36m2117
24Qwen3.8-Max0.0081$33.4299.7M1.3M15h 1m5748
25Gemini 3.8 Flash0.0058$23.48261.8M192k2h 8m5634
26Claude Opus 50.0048$110.39179.3M515k12h 40m4317
27Muse Spark 1.20.0047$67.55167.8M657k12h 12m5416
28Grok 4.60.0025$162.38158.0M937k10h 27m64914
29Gemini 3.8 Flash0.0021$39.53434.9M429k7h 2m111913
30Grok 4.60.0012$313.02296.5M1.9M18h 41m112019
31Qwen3.8-Max-09020.0009$28.6281.5M1.2M20h 5m3911
32Qwen3.8-Max-09020.0009$26.0076.8M998k20h 6m3872
33Grok 4.60.0007$96.0091.3M481k3h 53m3293
34Qwen3.8-Max0.0004$47.32149.7M1.5M17h 59m6513
35GLM-5.30.0004$46.58170.2M369k10h 37m5917
36Claude Haiku 5.50.0000$14.49235.4M958k9h 43m5943
37Claude Haiku 5.50.0000$14.92236.6M1.1M7h 37m5972
38Claude Opus 5.50.0000$159.94559.4M1.8M19h 25m132926
39Claude Fable 50.0000$202.86169.0M429k14h 47m43614
40GLM-5.30.0000$50.83180.8M386k12h 52m5764
41Claude Fable 5.10.0000$219.62392.8M963k7h 58m8449
42Muse Spark 1.20.0000$32.8165.0M127k4h 50m2763
43Claude Fable 5.10.0000$193.70342.2M936k9h 59m82011
44DeepSeek V4 Flash Vision Exp0.0000$2.44138.4M299k9h 52m5314
45Claude Haiku 5.50.0000$13.92215.0M1.1M9h 1m5133
46DeepSeek V4 Flash Vision Exp0.0000$5.46332.4M492k10h 53m78215
47Grok 4.70.0000$211.95219.1M541k7h 14m8765
48DeepSeek V4 Flash Vision Exp0.0000$3.59206.9M443k9h 31m59316
49Claude Opus 5.50.0000$183.76644.5M2.0M19h 7m147623
50Gemini 4 Argon0.0000$275.58621.4M1.5M15h 16m139122
51Kimi K30.0000$185.83517.0M1.5M20h 0m118813
52GPT-6 Astra0.0000$2665.441249.7M2.4M19h 33m269942
53GPT-5.6 Sol0.0000$109.76114.5M139k5h 57m4017
54Claude Sonnet 5.50.0000$131.29505.6M2.3M19h 12m12487
55Grok 4.70.0000$51.5950.1M157k1h 43m2125
56Gemini 4 Argon0.0000$100.53344.7M936k8h 35m8288
57Gemini 3.8 Flash0.0000$24.27258.5M198k4h 49m6073
58GLM-5.3 Flash0.0000$3.26101.7M249k9h 20m4787
59Claude Opus 5.50.0000$185.38644.4M2.1M18h 30m144729
60Claude Opus 50.0000$89.33141.7M467k15h 55m37611
61Inkling0.0000$4.875.1M12k1h 40m923
62Grok 4.70.0000$100.20104.5M326k3h 50m4705
63Claude Fable 5.10.0000$177.26316.2M794k11h 11m8339
64Gemini 4 Argon0.0000$197.19445.3M1.3M12h 41m10229
65Kimi K30.0000$246.45710.4M1.8M20h 0m173614
66Gemini 3.8 Flash0.0000$21.47225.2M181k2h 13m5715
67Muse Spark 1.30.0000$429.35454.7M706k19h 28m11658
68Claude Haiku 5.50.0000$24.57393.7M1.7M13h 34m9056
69Grok 4.70.0000$565.89566.8M1.5M11h 16m218910
70GLM-5.30.0000$68.85206.5M390k14h 23m60717
71Claude Sonnet 5.50.0000$90.56360.5M1.4M18h 46m8798
72Inkling0.0000$7.608.0M10k1h 46m1202
73Gemini 3.7 Flash0.0000$9.47100.2M149k1h 43m3164
74Muse Spark 1.30.0000$58.3660.2M197k8h 23m3863
75GPT-5.6 Sol0.0000$182.18175.0M189k6h 4m4858
76Inkling0.0000$5.185.4M12k1h 28m912
77DeepSeek V4 Flash Vision Exp0.0000$3.41198.5M360k8h 1m5624
78Claude Opus 5.50.0000$134.68471.5M1.5M18h 23m105921
79Grok 4.60.0000$419.76405.9M2.2M19h 4m158660
80GPT-6 Astra0.0000$2441.521153.7M2.1M19h 6m255341
81Claude Fable 5.10.0000$182.53329.2M746k9h 31m84121
82GPT-6 Astra0.0000$2574.701208.7M2.3M17h 31m262265
83GLM-5.3 Flash0.0000$5.76124.8M287k14h 48m4733
84Claude Opus 5.50.0000$150.29514.2M1.7M17h 0m120615
85Inkling0.0000$6.426.7M16k1h 12m1001
86DeepSeek V4 Flash Vision Exp0.0000$3.54209.2M364k8h 32m6329
87GPT-6 Astra0.0000$1722.33819.7M1.5M19h 18m184442
88Qwen3.8-Max0.0000$42.20143.0M952k17h 51m6041
89Kimi K30.0000$49.64141.5M328k6h 19m5297
90Inkling0.0000$14.7615.4M36k34m1942
91Claude Sonnet 5.50.0000$128.12516.0M1.9M18h 29m11958
92Gemini 3.7 Flash0.0000$9.0285.7M143k1h 52m3061
93Gemini 4 Argon0.0000$160.21500.1M1.5M13h 56m116920
94Claude Fable 50.0000$289.82249.1M515k7h 2m54312
95GLM-5.3 Flash0.0000$3.52102.4M346k8h 20m4182
96Qwen3.8-Max0.0000$47.25152.8M1.4M17h 10m6423
97GLM-5.3 Flash0.0000$5.38133.7M325k9h 34m5412
98Gemini 3.7 Flash0.0000$12.5890.8M182k4h 36m3171
99Kimi K30.0000$124.72355.5M911k15h 41m94824
100GLM-5.3 Flash0.0000$5.24138.3M282k10h 25m5423
101Qwen3.8-Max-09020.0000$29.4586.5M1.2M20h 1m4131
102Claude Fable 50.0000$175.12145.0M372k12h 9m42714
103Claude Sonnet 5.50.0000$140.54573.5M2.0M18h 42m13225
104Claude Fable 50.0000$186.99154.4M396k7h 35m4299
105Muse Spark 1.30.0000$52.36191.1M288k7h 43m6805
106Muse Spark 1.30.0000$73.5999.0M263k5h 24m4593
107Claude Opus 50.0000$158.96248.3M890k16h 5m69315
108Claude Fable 5.10.0000$226.14406.3M953k11h 14m90215
109Gemini 3.7 Flash0.0000$6.5851.9M91k1h 41m2964
110Qwen3.8-Max-09020.0000$22.3762.1M1.0M20h 3m3301

Snooker Prediction

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.6319$2653.821245.9M2.6M19h 52m276939
2GPT-6 Astra0.6316$2364.831112.0M2.4M19h 31m253951
3GPT-6 Astra0.6308$1877.69889.9M1.7M16h 9m199731
4GPT-6 Astra0.6304$348.12162.7M418k3h 11m4424
5Claude Opus 5.50.6243$92.07333.9M907k9h 5m81028
6Gemini 4 Argon0.6242$58.63165.8M890k6h 8m4182
7GPT-6 Astra0.6223$321.27149.5M395k3h 5m4014
8Claude Opus 5.50.6219$106.45401.8M928k15h 53m97739
9Claude Sonnet 5.50.6210$169.39673.2M2.7M19h 1m15102
10Claude Opus 5.50.6162$99.16365.9M934k14h 38m87624
11Claude Sonnet 5.50.6129$163.92638.8M2.8M17h 56m143320
12Claude Sonnet 5.50.6127$143.11580.3M2.1M18h 52m131529
13Claude Sonnet 5.50.6036$144.28579.6M2.2M18h 20m13258
14Gemini 4 Argon0.5920$39.04128.3M687k6h 49m3573
15Claude Sonnet 5.50.5773$121.18495.6M1.7M19h 1m110810
16Claude Opus 5.50.5538$119.85454.9M1.0M14h 11m101641
17Gemini 4 Argon0.5407$63.97191.0M855k6h 41m4643
18Claude Opus 5.50.5128$94.50346.2M909k11h 7m86412
19Claude Fable 5.10.5126$87.17154.8M404k6h 52m40812
20Claude Opus 50.5001$197.63316.4M1.0M15h 45m73024
21Claude Fable 5.10.4984$96.24173.0M403k7h 34m48621
22GPT-5.6 Sol0.4857$119.18111.7M242k2h 5m29911
23GPT-5.6 Sol0.4839$170.16165.0M275k4h 12m4329
24Claude Fable 5.10.4822$86.06152.3M409k8h 44m40223
25Claude Fable 5.10.4767$88.31156.7M413k3h 39m39710
26Claude Opus 50.4607$210.30340.0M1.1M18h 37m82119
27Gemini 4 Argon0.4552$134.67137.5M744k5h 5m3723
28GPT-5.6 Sol0.4428$157.87150.8M208k2h 34m3549
29Claude Fable 50.4405$329.75265.7M842k18h 32m62721
30Claude Opus 50.4307$172.30276.6M886k18h 12m66510
31GPT-5.6 Sol0.4295$132.32126.4M240k4h 1m3696
32Claude Haiku 5.50.4124$12.19184.2M1.1M9h 13m4523
33Muse Spark 1.30.3826$317.27411.4M767k19h 50m10324
34Grok 4.60.3789$466.11391.2M2.0M19h 43m148873
35Claude Fable 5.10.3738$86.02153.2M388k5h 28m4249
36Claude Fable 50.3600$264.94218.2M625k12h 41m43518
37Muse Spark 1.30.3439$236.90672.0M957k19h 49m15695
38Claude Fable 50.3089$197.41157.5M532k18h 2m36913
39Claude Haiku 5.50.3050$9.22147.7M647k7h 56m3072
40Grok 4.60.3048$106.1286.0M725k5h 58m3785
41GPT-5.6 Sol0.2890$179.27154.6M213k9h 23m3575
42Claude Haiku 5.50.2612$6.70101.8M570k4h 14m2522
43Claude Opus 50.2573$170.72274.5M864k18h 25m68512
44Claude Haiku 5.50.2379$13.72212.9M1.2M10h 26m52924
45Gemini 4 Argon0.2214$64.59161.0M705k6h 32m4203
46GLM-5.30.1976$71.12251.5M765k18h 56m65415
47Grok 4.60.1779$108.4587.9M851k6h 23m34415
48Claude Fable 50.1348$215.61174.0M561k17h 21m40212
49Claude Haiku 5.50.1195$6.94107.1M566k4h 29m2602
50Grok 4.60.1175$125.27104.6M768k11h 27m4469
51Gemini 3.8 Flash0.1105$14.99133.6M331k1h 42m4033
52GLM-5.30.1013$57.78201.7M793k14h 16m53113
53Qwen3.8-Max0.0882$56.82135.8M1.2M18h 54m5061
54Gemini 3.8 Flash0.0820$13.08117.4M334k1h 20m3683
55Claude Opus 50.0762$115.37188.1M559k19h 9m40711
56GLM-5.30.0590$53.37163.6M430k17h 18m3736
57Muse Spark 1.30.0370$445.62445.7M615k19h 19m8578
58Qwen3.8-Max-09020.0341$31.7857.0M1.5M20h 7m2981
59Inkling0.0335$2.612.6M26k1h 16m722
60GLM-5.30.0311$89.97246.3M519k19h 15m49513
61Claude Fable 50.0276$244.97201.6M586k17h 26m45716
62Qwen3.8-Max-09020.0275$32.6959.4M1.3M20h 2m3031
63Grok 4.60.0252$77.1660.3M816k4h 29m27113
64Inkling0.0203$2.912.9M46k1h 53m872
65Grok 4.70.0086$81.1779.8M486k3h 8m3325
66Kimi K30.0000$126.53346.0M738k19h 31m7788
67Muse Spark 1.30.0000$518.18574.1M1.1M19h 44m12906
68Qwen3.8-Max0.0000$80.65199.9M2.1M18h 39m6731
69Gemini 3.7 Flash0.0000$7.8266.5M374k1h 5m2791
70Grok 4.70.0000$342.95338.0M1.2M19h 47m137039
71Qwen3.8-Max-09020.0000$38.3677.8M1.3M20h 2m3451
72Gemini 3.7 Flash0.0000$8.3359.1M343k2h 40m2823
73Inkling0.0000$3.243.2M40k1h 45m1031
74Gemini 3.7 Flash0.0000$5.6140.2M288k59m2242
75Gemini 3.8 Flash0.0000$8.1176.9M253k1h 6m2995
76Qwen3.8-Max-09020.0000$30.6766.2M1.6M20h 2m2681
77Muse Spark 1.20.0000$26.92100.5M603k1h 48m3775
78DeepSeek V4 Flash Vision Exp0.0000$4.83277.6M638k5h 11m64413
79Muse Spark 1.20.0000$12.0849.7M275k1h 6m2508
80DeepSeek V4 Flash Vision Exp0.0000$3.23179.6M479k19h 58m4661
81GLM-5.3 Flash0.0000$8.45217.9M542k13h 37m5203
82DeepSeek V4 Flash Vision Exp0.0000$3.55189.8M629k6h 0m4853
83Qwen3.8-Max0.0000$115.97289.9M2.1M19h 35m8111
84Qwen3.8-Max0.0000$102.79307.3M1.7M19h 10m7942
85Gemini 3.7 Flash0.0000$6.6448.6M323k1h 55m2471
86Grok 4.70.0000$282.03285.1M1.2M19h 51m119149
87Qwen3.8-Max-09020.0000$28.0761.6M1.3M20h 0m2871
88Kimi K30.0000$140.38372.9M1.4M19h 51m92526
89Gemini 3.8 Flash0.0000$8.7083.2M282k1h 15m3121
90Inkling0.0000$2.842.7M69k45m822
91Muse Spark 1.20.0000$16.1178.5M517k1h 19m3094
92Qwen3.8-Max0.0000$61.40180.5M1.6M20h 1m5511
93GLM-5.3 Flash0.0000$10.25278.8M597k10h 31m5968
94Inkling0.0000$1.801.8M26k14m792
95Muse Spark 1.20.0000$13.7075.9M319k1h 35m3053
96GLM-5.3 Flash0.0000$13.39288.1M552k17h 55m64019
97Grok 4.70.0000$61.2564.2M387k4h 4m3355
98Kimi K30.0000$122.14346.5M798k19h 47m7938
99Gemini 3.7 Flash0.0000$7.4056.9M413k1h 21m2662
100DeepSeek V4 Flash Vision Exp0.0000$4.28248.4M549k14h 16m5938
101Kimi K30.0000$117.31316.7M1.0M19h 47m8066
102Kimi K30.0000$105.21273.3M660k20h 0m5483
103Grok 4.70.0000$79.8685.0M390k6h 4m38413
104Gemini 3.8 Flash0.0000$17.30177.6M409k1h 51m4715
105Muse Spark 1.30.0000$449.88491.2M832k19h 52m11762
106GLM-5.3 Flash0.0000$7.94248.0M455k19h 56m5957
107GLM-5.30.0000$94.15290.7M465k18h 52m62711
108DeepSeek V4 Flash Vision Exp0.0000$5.35314.7M642k14h 37m7093
109GLM-5.3 Flash0.0000$12.92278.9M847k19h 47m6871
110Muse Spark 1.20.0000$16.5887.1M508k2h 14m3216

SPICE Circuit Simulator in Rust

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Argon0.9394$221.62329.8M1.9M11h 7m7313
2Claude Opus 5.50.9293$97.56280.4M1.6M6h 22m66314
3Claude Sonnet 5.50.9293$109.70401.0M2.3M10h 14m90522
4Claude Sonnet 5.50.9293$116.79422.3M2.6M15h 25m94716
5Claude Sonnet 5.50.9192$157.47595.8M3.0M11h 25m12664
6Claude Sonnet 5.50.9192$114.22425.5M2.3M14h 29m92218
7Gemini 4 Argon0.9091$147.35234.0M1.0M8h 39m5036
8GPT-6 Astra0.9091$2887.401385.4M2.5M19h 50m3121180
9Claude Opus 5.50.8990$72.19195.2M1.3M4h 28m43413
10GPT-6 Astra0.8990$347.32164.1M405k2h 56m4147
11Claude Sonnet 5.50.8990$108.09389.8M2.4M13h 20m87312
12GPT-6 Astra0.8990$599.18284.8M531k4h 2m6167
13GPT-6 Astra0.8889$677.88324.1M558k4h 32m6947
14Claude Fable 50.8889$545.26410.4M1.8M15h 21m93213
15Gemini 4 Argon0.8889$270.20399.0M2.4M13h 19m8836
16Gemini 4 Argon0.8788$203.70185.4M882k6h 7m4263
17Claude Opus 5.50.8687$65.56170.6M1.2M3h 47m3996
18Claude Opus 5.50.8687$104.48301.0M1.7M5h 14m73111
19GPT-6 Astra0.8687$172.7283.5M308k2h 47m2884
20Claude Opus 5.50.8687$69.51187.1M1.2M4h 12m42715
21Claude Fable 5.10.8586$166.41276.3M1.2M9h 57m63217
22Claude Opus 50.8485$441.42701.9M2.4M13h 28m152438
23Claude Fable 50.8384$451.15353.8M1.3M8h 53m73311
24Gemini 4 Argon0.8283$51.57147.9M741k4h 35m4035
25Claude Fable 50.8081$505.54407.1M1.3M17h 12m85716
26Claude Opus 50.7879$564.99947.9M2.4M15h 22m198033
27Claude Fable 50.7778$491.30392.4M1.3M15h 56m85113
28Claude Fable 50.7778$474.28378.9M1.3M17h 20m80012
29Claude Opus 50.7677$321.00503.6M1.9M12h 46m109231
30Claude Fable 5.10.7677$93.05145.4M837k3h 54m4174
31Grok 4.70.7576$721.50746.3M2.8M15h 40m309416
32Claude Opus 50.7475$357.80576.4M1.9M14h 22m123323
33Claude Opus 50.7475$479.75767.1M2.6M12h 42m155722
34Grok 4.70.7172$780.09794.5M2.5M20h 0m328018
35Claude Fable 5.10.7071$96.79153.4M827k4h 2m4138
36Grok 4.70.7071$747.81772.9M3.1M17h 23m326717
37Claude Fable 5.10.6970$69.08107.8M623k2h 37m2272
38Grok 4.70.6970$807.64821.4M3.2M17h 39m336444
39Claude Fable 5.10.6667$96.05148.5M898k4h 16m4066
40Gemini 3.7 Flash0.6263$99.311037.7M2.0M6h 16m25774
41Grok 4.70.6061$843.32872.9M3.2M19h 50m363616
42Muse Spark 1.30.5758$268.721376.2M2.2M19h 51m33282
43Grok 4.60.5657$717.25714.4M2.7M18h 22m2483266
44Muse Spark 1.30.5657$460.65531.6M1.1M17h 48m13474
45Claude Haiku 5.50.5556$14.47224.0M1.1M2h 40m5572
46Claude Haiku 5.50.5556$12.80192.7M1.2M2h 43m5104
47Muse Spark 1.30.5455$559.10664.1M1.1M19h 47m15405
48Gemini 3.8 Flash0.5354$35.82384.7M639k3h 11m9654
49Claude Haiku 5.50.5354$11.83178.7M1.1M2h 15m4372
50GLM-5.30.5354$171.96618.6M1.7M18h 15m14414
51Gemini 3.7 Flash0.5253$121.421230.5M2.0M12h 5m29493
52Grok 4.60.5253$835.65836.5M3.1M20h 0m3128205
53GLM-5.3 Flash0.5051$24.75719.3M1.5M17h 38m17251
54GLM-5.30.4949$235.96867.9M1.6M17h 11m190518
55Grok 4.60.4848$586.10582.0M3.0M17h 34m232289
56Gemini 3.7 Flash0.4747$76.85790.2M1.6M4h 46m20172
57GLM-5.3 Flash0.4646$19.29592.9M1.1M15h 32m14004
58Grok 4.60.4646$1191.201187.2M2.5M19h 58m387996
59Muse Spark 1.30.4646$547.17608.4M1.3M19h 44m13313
60Grok 4.60.4545$165.93154.1M860k5h 37m56337
61Gemini 3.7 Flash0.4444$80.51766.1M1.3M6h 23m17937
62GPT-5.6 Sol0.4444$366.07350.2M455k6h 25m79722
63GLM-5.30.4444$158.88578.0M1.3M10h 53m11554
64Qwen3.8-Max-09020.4242$87.16281.5M2.5M19h 59m6011
65Gemini 3.8 Flash0.4242$24.11264.9M400k1h 50m6102
66GLM-5.30.4141$190.24693.2M1.5M19h 41m170530
67GPT-5.6 Sol0.4141$307.32296.1M386k4h 30m78315
68Qwen3.8-Max-09020.4040$64.29188.8M2.6M20h 1m5161
69GPT-5.6 Sol0.3939$538.95528.2M617k6h 30m128021
70Muse Spark 1.30.3939$557.80621.9M1.5M19h 58m13911
71GLM-5.3 Flash0.3737$22.66655.9M1.7M20h 0m16441
72Gemini 3.7 Flash0.3737$126.281246.3M2.0M12h 6m29212
73Qwen3.8-Max0.3737$145.98524.1M2.1M19h 26m13381
74GLM-5.3 Flash0.3737$15.05404.9M975k14h 18m9752
75Qwen3.8-Max-09020.3737$124.78385.3M4.3M20h 1m9892
76Claude Haiku 5.50.3636$10.69164.8M919k2h 31m4051
77Claude Haiku 5.50.3636$14.75230.3M1.1M2h 56m5391
78Qwen3.8-Max0.3434$127.04463.9M1.6M19h 13m9874
79GLM-5.3 Flash0.3434$27.30749.1M1.3M19h 17m15993
80GPT-5.6 Sol0.3333$187.27186.7M262k2h 15m5158
81Gemini 3.8 Flash0.3232$15.32160.0M291k1h 17m4263
82GLM-5.30.3131$152.26545.3M1.3M16h 57m116423
83Qwen3.8-Max-09020.3030$73.95234.0M2.3M20h 1m4701
84Qwen3.8-Max0.3030$96.60342.7M1.6M18h 43m7602
85Qwen3.8-Max0.3030$110.14386.5M2.0M19h 56m9471
86Qwen3.8-Max0.2727$126.58455.7M1.9M19h 26m9517
87GPT-5.6 Sol0.2626$226.84221.2M327k3h 7m59213
88Qwen3.8-Max-09020.2020$65.44194.8M2.5M19h 35m4442
89Muse Spark 1.20.1313$32.05183.6M731k2h 8m4651
90Gemini 3.8 Flash0.0808$2.1615.8M108k23m1421
91Muse Spark 1.20.0707$10.8153.3M351k1h 35m2232
92Muse Spark 1.20.0707$32.82175.7M815k3h 21m4611
93Muse Spark 1.20.0505$8.7748.8M242k1h 16m1962
94Muse Spark 1.20.0404$5.3427.9M188k26m1432
95Gemini 3.8 Flash0.0101†$2.2617.9M93k20m1402
96DeepSeek V4 Flash Vision Exp0.0000$11.65704.6M1.2M10h 40m154915
97Kimi K30.0000$179.57474.0M1.9M19h 42m12159
98Kimi K30.0000$215.15588.2M1.9M19h 56m14053
99DeepSeek V4 Flash Vision Exp0.0000$19.651192.1M2.0M18h 3m239810
100Kimi K30.0000$199.08565.4M1.4M19h 58m12711
101Kimi K30.0000$204.94570.3M1.7M19h 34m13993
102Kimi K30.0000$193.03529.1M1.8M19h 58m12631
103DeepSeek V4 Flash Vision Exp0.0000$20.481199.6M2.4M11h 32m25639
104Inkling0.0000$4.424.6M23k45m831
105DeepSeek V4 Flash Vision Exp0.0000$21.511287.0M2.2M19h 10m290413
106Inkling0.0000$19.3020.1M40k1h 20m1702
107Inkling0.0000$1.041.1M10k27m522
108DeepSeek V4 Flash Vision Exp0.0000$19.681182.5M2.0M19h 8m261723
109Inkling0.0000$5.075.3M18k1h 13m1102
110Inkling0.0000$5.215.3M32k15m1242

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Stepper Music Sequencer GBA

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.9974$3129.481515.4M2.4M19h 55m337649
2Claude Opus 5.50.9917$247.64942.3M2.2M18h 17m206331
3GPT-6 Astra0.9897$2759.221308.1M2.5M19h 59m294238
4Claude Opus 5.50.9883$203.46765.3M1.9M19h 3m175733
5Claude Opus 5.50.9874$283.791107.1M2.3M19h 19m23568
6Claude Opus 5.50.9866$313.811197.7M2.7M18h 20m270844
7GPT-6 Astra0.9861$2721.061296.9M2.6M19h 56m297826
8Claude Opus 5.50.9844$258.85972.6M2.4M18h 43m221122
9Claude Sonnet 5.50.9834$194.76804.6M2.6M19h 42m18645
10GPT-6 Astra0.9793$2755.431303.4M2.5M19h 59m291637
11Claude Sonnet 5.50.9789$233.93974.2M3.0M19h 16m21412
12Claude Sonnet 5.50.9751$203.75838.4M2.8M19h 30m18641
13Claude Sonnet 5.50.9732$218.44904.4M2.9M19h 31m20182
14Claude Sonnet 5.50.9677$205.23838.3M3.0M19h 27m19476
15Claude Fable 5.10.9662$443.40798.0M1.8M18h 14m180227
16GPT-6 Astra0.9655$2773.421319.2M2.5M19h 57m294130
17Gemini 4 Argon0.9654$544.95521.5M2.1M21h 0m11623
18Claude Fable 5.10.9569$440.73799.7M1.7M15h 10m182514
19Claude Opus 50.9533$570.71935.1M2.7M19h 25m206023
20Gemini 4 Argon0.9520$272.84638.9M3.5M20h 55m13824
21Claude Fable 5.10.9473$365.73654.8M1.6M15h 4m152120
22Claude Fable 5.10.9459$457.39831.4M1.7M14h 37m184932
23Gemini 4 Argon0.9258$445.36558.0M2.3M20h 59m12651
24Gemini 4 Argon0.9237$409.68593.6M2.6M20h 55m14457
25Gemini 4 Argon0.9165$187.49667.9M3.3M20h 59m15072
26Claude Haiku 5.50.9129$66.381065.9M4.7M16h 56m238411
27Claude Fable 5.10.9053$549.231015.6M1.7M16h 2m223418
28Claude Opus 50.8947$669.611119.9M2.9M19h 5m246232
29Claude Fable 50.8760$652.52521.9M1.8M18h 59m121615
30Claude Opus 50.8643$526.73857.9M2.6M14h 11m179132
31Claude Fable 50.8612$916.45747.8M2.3M18h 51m171916
32Claude Opus 50.8500$580.43975.9M2.5M18h 59m210331
33Claude Opus 50.8367$450.82756.2M1.9M15h 49m156011
34GPT-5.6 Sol0.7701$944.54934.7M1.1M15h 1m241121
35Grok 4.70.7472$628.06649.9M2.0M11h 13m261863
36Claude Haiku 5.50.7427$60.68993.0M4.0M15h 28m226913
37GPT-5.6 Sol0.7406$409.56413.9M542k8h 34m125115
38Claude Fable 50.7325$725.08587.9M1.9M18h 21m129912
39GPT-5.6 Sol0.7219$253.31245.2M326k3h 19m6796
40Claude Haiku 5.50.7208$38.44612.0M2.8M8h 23m13252
41Claude Fable 50.7151$484.68385.7M1.3M18h 44m83711
42Claude Haiku 5.50.6803$24.48387.9M1.9M5h 8m9356
43Claude Haiku 5.50.6608$61.93983.3M4.6M18h 17m215615
44Claude Fable 50.6534$728.09583.8M2.0M17h 53m12646
45GLM-5.30.6108$356.801301.6M3.0M19h 1m267119
46GPT-5.6 Sol0.6048$566.59550.5M752k14h 19m151311
47Grok 4.70.6012$1385.341395.4M3.2M19h 29m506467
48Grok 4.60.5671$305.84301.9M2.2M11h 0m122745
49Muse Spark 1.30.5524$214.491195.2M2.0M12h 19m28461
50Kimi K30.5098$230.68643.2M1.9M20h 0m15453
51GPT-5.6 Sol0.4981$490.17481.7M531k5h 24m127432
52Grok 4.70.4771$380.66393.3M1.3M7h 10m159732
53GLM-5.30.4715$281.501008.4M2.3M16h 6m226416
54Grok 4.70.4712$1073.481101.7M3.6M19h 4m4513110
55Grok 4.70.4415$440.85450.4M1.7M8h 48m186319
56GLM-5.30.4046$276.191010.3M1.8M15h 31m207021
57Gemini 3.8 Flash0.4044$62.09665.3M979k9h 34m16632
58Muse Spark 1.30.3727$330.621484.1M2.3M19h 59m330530
59Kimi K30.3706$227.60629.2M1.9M19h 47m15042
60Gemini 3.8 Flash0.3444$76.61826.4M1.1M12h 14m19524
61GLM-5.30.3427$275.261018.0M1.7M17h 39m209039
62Grok 4.60.3420$868.26872.5M3.4M16h 30m3114373
63Kimi K30.3170$227.44622.4M1.9M19h 52m14391
64Muse Spark 1.30.3146$507.64559.8M1.1M19h 23m13542
65Gemini 3.8 Flash0.3068$59.22604.8M923k9h 13m15074
66Gemini 3.8 Flash0.2640$52.50504.3M779k8h 9m11884
67Grok 4.60.2607$223.96223.8M1.5M7h 20m88218
68Grok 4.60.2416$205.23195.4M1.9M7h 34m79228
69Gemini 3.7 Flash0.2415$49.29499.9M1.0M4h 48m13022
70Grok 4.60.2197$129.50120.8M2.0M7h 52m54019
71GLM-5.3 Flash0.2060$16.51502.4M1.2M10h 2m12356
72Gemini 3.7 Flash0.1895$40.63436.9M982k3h 1m11342
73Gemini 3.7 Flash0.1724$88.83943.5M2.1M6h 27m24491
74Gemini 3.7 Flash0.1698$29.14318.3M646k2h 19m8562
75Gemini 3.8 Flash0.1660$58.00614.2M934k9h 4m15642
76GLM-5.30.1440$63.57232.5M498k3h 14m4876
77DeepSeek V4 Flash Vision Exp0.1348$19.481192.0M1.8M11h 51m26707
78Kimi K30.1336$196.38508.8M1.8M19h 51m12094
79Gemini 3.7 Flash0.1224$55.17592.3M1.3M5h 23m15075
80DeepSeek V4 Flash Vision Exp0.1138$28.551772.4M2.4M15h 1m383323
81GLM-5.3 Flash0.1080$14.12436.5M1.1M11h 4m9827
82Kimi K30.0909$184.74495.2M1.5M19h 58m11542
83GLM-5.3 Flash0.0899$16.14483.9M1.1M17h 24m11123
84Muse Spark 1.30.0797$528.52575.6M1.2M19h 59m13131
85DeepSeek V4 Flash Vision Exp0.0534$18.461143.5M1.6M13h 42m270016
86Muse Spark 1.30.0480$556.48567.3M735k19h 51m11075
87DeepSeek V4 Flash Vision Exp0.0419$18.931164.8M1.7M11h 44m276429
88DeepSeek V4 Flash Vision Exp0.0319$17.221033.6M1.8M11h 35m230613
89GLM-5.3 Flash0.0244$12.30358.8M925k17h 17m8941
90Qwen3.8-Max0.0240$114.04338.0M2.8M19h 40m8846
91Qwen3.8-Max0.0224$119.80401.3M2.9M20h 1m934—
92GLM-5.3 Flash0.0188$8.33220.9M946k17h 57m6051
93Qwen3.8-Max0.0183$113.87373.6M3.0M19h 42m990—
94Muse Spark 1.20.0175$37.47155.3M1.3M5h 29m4607
95Qwen3.8-Max0.0159$129.76393.1M2.8M19h 53m1102—
96Qwen3.8-Max0.0002$139.67464.7M2.7M19h 56m1203—
97Qwen3.8-Max-09020.0000$43.55102.3M1.5M20h 4m4281
98Qwen3.8-Max-09020.0000$38.2781.2M1.4M20h 9m4211
99Qwen3.8-Max-09020.0000$38.1091.8M1.7M20h 3m4131
100Qwen3.8-Max-09020.0000$31.8860.8M1.6M20h 2m3901
101Inkling0.0000$3.823.9M21k15m1032
102Qwen3.8-Max-09020.0000$41.37105.1M1.6M20h 8m4361
103Inkling0.0000$6.626.9M28k22m1681
104Inkling0.0000$8.488.8M35k24m1712
105Muse Spark 1.20.0000$44.79140.1M936k4h 21m5434
106Inkling0.0000$10.6411.1M32k19m1931
107Muse Spark 1.20.0000†$4.6818.3M123k58m1562
108Muse Spark 1.20.0000†$53.1995.9M776k4h 50m3512
109Inkling0.0000$5.725.9M31k22m1402
110Muse Spark 1.20.0000†$10.5943.3M223k2h 38m2593

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Synthetic Music Diarization

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.5899$503.76243.1M455k15h 19m59111
2GPT-6 Astra0.5838$329.84157.1M371k18h 6m42613
3GPT-6 Astra0.5821$102.5750.4M226k17h 2m2148
4GPT-6 Astra0.5755$313.33152.4M361k17h 42m45912
5Gemini 4 Argon0.5622$95.7586.8M749k11h 34m2767
6Gemini 4 Argon0.5493$59.7663.4M476k9h 43m2015
7Claude Sonnet 5.50.5485$40.25163.7M585k16h 59m3776
8Claude Sonnet 5.50.5468$52.30219.6M652k16h 9m4566
9Claude Opus 5.50.5460$17.7255.1M249k18h 32m25612
10Claude Fable 5.10.5457$12.1118.5M118k17h 49m1568
11Claude Sonnet 5.50.5456$46.15192.4M590k18h 34m4204
12Gemini 4 Argon0.5456$46.2659.1M483k7h 58m1695
13Claude Sonnet 5.50.5444$47.19194.7M641k18h 8m4141
14Claude Sonnet 5.50.5410$38.75155.4M594k16h 3m3638
15Claude Opus 5.50.5369$24.8483.3M302k17h 50m3107
16Claude Opus 5.50.5369$16.9751.1M254k18h 25m24110
17Claude Opus 50.5368$28.6338.3M258k18h 34m2028
18Claude Fable 5.10.5346$11.4117.0M120k17h 44m1587
19Claude Opus 50.5328$33.9547.5M267k18h 38m2177
20Gemini 4 Argon0.5249$103.39100.4M544k9h 12m2468
21GPT-5.6 Sol0.5247$44.1953.3M154k7h 34m2673
22Claude Opus 50.5241$22.9629.3M223k18h 54m1755
23Claude Opus 5.50.5219$17.3851.6M265k17h 34m2438
24Claude Haiku 5.50.5197$5.7894.3M402k14h 17m3062
25Claude Fable 50.5170$40.5426.3M193k18h 24m1796
26Claude Fable 5.10.5104$17.6028.7M134k17h 45m23011
27Claude Fable 50.5096$41.0827.2M188k19h 7m1846
28Claude Fable 50.5079$49.4533.2M218k18h 55m1968
29GPT-5.6 Sol0.5065$80.6578.5M178k15h 57m33911
30GPT-6 Astra0.5062$228.20112.0M318k15h 43m37915
31GPT-5.6 Sol0.4952$59.6269.7M147k15h 37m3593
32Claude Opus 5.50.4919$19.7261.9M269k17h 35m2469
33Claude Fable 50.4917$51.3235.9M209k18h 41m2286
34Claude Fable 5.10.4905$10.2915.1M114k17h 40m1407
35Claude Fable 5.10.4889$10.8615.6M125k15h 34m1386
36Qwen3.8-Max-09020.4844$67.12233.9M1.2M19h 8m6454
37Qwen3.8-Max-09020.4840$91.60324.7M1.4M19h 50m7931
38Claude Haiku 5.50.4839$3.5755.3M334k17h 2m2365
39Claude Opus 50.4833$26.8234.5M255k17h 35m1813
40GLM-5.30.4816$35.34125.4M361k17h 30m46211
41Qwen3.8-Max-09020.4814$101.81367.2M1.4M19h 10m8182
42Claude Haiku 5.50.4805$3.7058.7M322k17h 54m2493
43GLM-5.30.4802$31.6279.0M303k18h 9m3611
44Gemini 3.7 Flash0.4776$32.86129.1M265k12h 34m4382
45GPT-5.6 Sol0.4737$78.7876.5M133k14h 47m2864
46GPT-5.6 Sol0.4727$68.5982.8M153k14h 29m4257
47Gemini 3.8 Flash0.4726$11.8472.7M176k4h 47m2926
48GLM-5.3 Flash0.4723$1.6748.7M181k16h 18m2945
49Gemini 3.7 Flash0.4664$11.2742.4M155k7h 29m2542
50Grok 4.60.4661$133.75133.0M655k19h 52m57842
51Qwen3.8-Max0.4605$29.62103.3M529k18h 43m50911
52GLM-5.30.4602$19.7741.7M196k19h 9m2534
53Grok 4.70.4597$72.6761.2M249k8h 6m2494
54Muse Spark 1.30.4569$29.57105.7M282k17h 55m5198
55Grok 4.70.4458$66.8549.2M265k14h 13m20510
56Qwen3.8-Max0.4425$26.6693.3M455k18h 13m4788
57Gemini 3.7 Flash0.4422$14.36133.2M250k5h 49m3892
58Claude Haiku 5.50.4413$4.5875.8M323k15h 34m2883
59DeepSeek V4 Flash Vision Exp0.4412$1.7293.1M282k19h 4m4302
60Grok 4.70.4406$208.39177.1M399k19h 30m6124
61Gemini 3.8 Flash0.4403$11.0095.0M185k4h 2m3345
62Claude Haiku 5.50.4371$5.4088.7M390k16h 43m3162
63Muse Spark 1.30.4340$126.99121.2M301k15h 7m4379
64Grok 4.60.4323$188.19192.5M1.1M19h 45m87156
65Kimi K30.4318$13.3633.2M179k18h 52m2445
66Qwen3.8-Max0.4301$34.00119.2M572k19h 17m50810
67GLM-5.30.4285$28.0377.4M258k18h 22m3669
68Grok 4.70.4284$43.8732.2M197k17h 17m1801
69GLM-5.30.4265$27.2778.5M240k19h 37m3746
70Gemini 3.7 Flash0.4264$42.51256.4M394k13h 10m6819
71DeepSeek V4 Flash Vision Exp0.4247$2.96173.2M352k17h 55m6174
72Muse Spark 1.30.4243$152.31160.5M376k14h 14m5007
73Gemini 4 Argon0.4215$32.5449.3M491k6h 13m1595
74Muse Spark 1.30.4206$121.45118.8M279k16h 52m51021
75Kimi K30.4157$22.8160.7M202k19h 10m3477
76Grok 4.60.4120$228.84232.3M993k19h 44m91863
77Grok 4.70.4074$96.1879.9M265k13h 36m3078
78DeepSeek V4 Flash Vision Exp0.4065$1.7395.5M262k17h 34m4485
79Gemini 3.8 Flash0.4043$7.6163.4M182k2h 25m2874
80Qwen3.8-Max0.4043$33.94117.1M655k18h 57m5015
81Kimi K30.4034$13.3431.5M191k18h 19m2474
82GLM-5.3 Flash0.4027$2.5572.6M225k19h 1m3918
83Qwen3.8-Max-09020.4015$71.54249.6M1.3M19h 38m6662
84Gemini 3.7 Flash0.4000$15.6783.4M201k4h 25m3221
85Grok 4.60.3985$299.53304.5M1.6M19h 27m128154
86Muse Spark 1.30.3962$92.9691.1M258k17h 50m45410
87Qwen3.8-Max0.3951$17.0256.1M424k19h 10m3914
88Gemini 3.8 Flash0.3938$11.3462.3M164k3h 35m30012
89GLM-5.3 Flash0.3907$3.7372.3M226k17h 49m3563
90Gemini 3.8 Flash0.3868$17.1391.7M227k6h 49m3608
91Kimi K30.3852$16.4839.9M237k19h 5m2342
92Muse Spark 1.20.3829$88.55356.6M541k7h 12m7543
93GLM-5.3 Flash0.3822$3.4756.4M213k17h 57m3403
94DeepSeek V4 Flash Vision Exp0.3803$1.8599.9M306k18h 37m4553
95Muse Spark 1.20.3711$10.8742.0M256k3h 30m2274
96Qwen3.8-Max-09020.3707$81.42285.5M1.4M19h 28m7102
97Kimi K30.3635$16.0039.1M227k18h 59m2346
98Muse Spark 1.20.3611$12.5032.3M167k4h 4m2135
99GLM-5.3 Flash0.3570$5.1263.4M220k18h 51m3423
100Muse Spark 1.20.3544$13.5350.0M335k4h 26m2484
101Muse Spark 1.20.3434$13.4047.8M217k5h 21m2415
102DeepSeek V4 Flash Vision Exp0.2979$2.02115.0M266k19h 32m5084
103Claude Fable 50.2496$50.5832.8M242k18h 51m1835
104Claude Opus 50.2240$27.3835.8M258k19h 9m1869
105Inkling0.2089$6.226.4M44k35m1312
106Inkling0.0477$6.406.6M38k28m1231
107Inkling0.0074$12.0812.5M45k59m1601
108Inkling0.0053$5.675.8M48k1h 31m992
109Inkling0.0012$9.519.9M36k38m1701
110Grok 4.60.0000$501.54509.4M1.9M18h 17m193796

Verilog Simulator in Swift

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9521$121.24461.6M1.1M7h 20m98914
2GPT-6 Astra0.9503$104.5349.0M213k1h 48m1875
3Claude Opus 5.50.9486$185.48723.5M1.5M11h 40m169526
4GPT-6 Astra0.9469$329.41155.6M366k2h 26m40926
5GPT-6 Astra0.9452$47.7326.0M162k1h 5m1303
6Claude Opus 5.50.9452$119.27459.4M1.0M7h 41m102514
7Claude Opus 5.50.9435$112.90428.3M1.0M8h 8m98911
8Claude Opus 5.50.9401$117.75445.5M1.1M6h 29m102413
9Claude Sonnet 5.50.9384$170.55724.9M2.0M18h 31m173912
10Gemini 4 Argon0.9349$95.9383.0M397k2h 56m1992
11GPT-6 Astra0.9349$94.8544.6M216k1h 33m1746
12Claude Sonnet 5.50.9332$135.20567.6M1.7M12h 14m12446
13Claude Fable 5.10.9332$262.30478.6M947k9h 23m114817
14Claude Fable 5.10.9315$216.99391.4M878k7h 55m9666
15Claude Sonnet 5.50.9315$217.23922.9M2.5M15h 59m217616
16Claude Fable 50.9298$976.76847.7M1.7M19h 7m200324
17Gemini 4 Argon0.9281$95.8972.5M365k2h 52m1783
18Gemini 4 Argon0.9281$83.8872.7M366k2h 46m1663
19Claude Sonnet 5.50.9281$215.60910.8M2.6M18h 12m212220
20Claude Fable 50.9264$317.64267.5M691k8h 11m49915
21GPT-6 Astra0.9264$71.9536.3M192k1h 35m1626
22Claude Sonnet 5.50.9264$186.02788.1M2.2M13h 56m169213
23Claude Opus 50.9212$529.35935.4M1.6M17h 43m214824
24Gemini 4 Argon0.9212$27.8068.8M403k2h 11m1654
25Claude Fable 5.10.9195$211.66382.5M840k9h 40m98917
26Claude Fable 50.9178$1055.99927.6M1.7M18h 46m223222
27Claude Opus 50.9178$356.58629.0M1.1M18h 31m139116
28Gemini 4 Argon0.9178$56.5079.3M431k2h 53m1912
29Claude Fable 5.10.9161$266.36483.7M1.0M10h 14m116734
30Claude Fable 50.9144$317.29267.0M700k14h 26m48317
31Claude Opus 50.9127$588.341052.2M1.6M19h 25m236425
32Claude Opus 50.9110$505.22890.6M1.6M16h 8m200621
33Claude Fable 5.10.9092$168.96308.4M606k6h 47m58610
34Claude Fable 50.8973$914.45785.4M1.7M18h 23m184335
35Claude Haiku 5.50.8938$55.29968.3M2.6M12h 1m205613
36Claude Opus 50.8921$377.04660.7M1.2M15h 32m140321
37Grok 4.70.8853$200.79205.0M994k5h 44m8531
38GPT-5.6 Sol0.8853$427.16420.2M394k14h 37m9219
39Claude Haiku 5.50.8818$45.82813.0M1.9M7h 26m17214
40Claude Haiku 5.50.8784$81.941434.4M3.8M19h 26m316245
41Grok 4.70.8784$244.06246.8M1.1M15h 21m100527
42Claude Haiku 5.50.8767$71.121257.3M3.0M15h 14m27395
43Claude Haiku 5.50.8733$40.39708.0M1.8M7h 30m15502
44GPT-5.6 Sol0.8596$271.89260.9M315k4h 56m6505
45Grok 4.70.8596$839.06861.8M2.3M19h 58m350737
46Grok 4.70.8510$180.74176.1M878k5h 58m6584
47GPT-5.6 Sol0.8493$335.11326.9M349k4h 23m7469
48Grok 4.70.8476$334.11341.6M1.2M11h 19m145747
49Kimi K30.8373$248.18704.4M1.6M20h 0m163611
50GPT-5.6 Sol0.8339$184.09180.1M273k4h 24m4806
51Gemini 3.7 Flash0.8305$103.651018.6M2.0M19h 58m24181
52Gemini 3.8 Flash0.8305$76.00821.2M1.2M6h 11m190822
53Gemini 3.8 Flash0.8288$123.531333.0M1.9M13h 23m305362
54Gemini 3.7 Flash0.8288$74.39745.3M2.1M17h 44m18281
55Gemini 3.8 Flash0.8253$99.981070.4M1.6M7h 37m241747
56Grok 4.60.8253$223.65211.2M1.9M12h 53m88431
57GLM-5.30.8236$236.70879.4M1.3M20h 1m192411
58GPT-5.6 Sol0.8236$181.11176.3M277k4h 52m4763
59Qwen3.8-Max-09020.8219$182.82643.3M3.3M19h 35m15293
60Gemini 3.7 Flash0.8202$75.29725.4M1.4M19h 4m16512
61Gemini 3.8 Flash0.8151$108.321181.2M1.8M8h 5m267141
62GLM-5.30.8151$195.25722.0M1.1M19h 28m170610
63Grok 4.60.8116$347.28325.2M2.2M19h 55m122256
64Qwen3.8-Max-09020.8099$199.79724.6M2.6M19h 4m183012
65Gemini 3.8 Flash0.8099$133.851223.1M1.9M19h 59m283411
66GLM-5.30.7757$229.93817.6M1.1M19h 47m180019
67GLM-5.30.7723$247.89875.5M1.2M19h 55m180417
68Kimi K30.7551$141.93387.6M1.1M20h 1m10091
69Qwen3.8-Max0.7551$162.17597.6M1.8M19h 37m14911
70GLM-5.30.7551$285.371061.6M1.4M19h 46m236723
71Grok 4.60.7517$518.10508.9M2.5M19h 53m184250
72Kimi K30.7175$256.44747.8M1.5M20h 1m16692
73Grok 4.60.6901$168.65160.9M1.6M9h 35m69125
74Kimi K30.6849$265.41774.0M1.6M19h 54m16822
75Qwen3.8-Max-09020.6473$162.62575.2M2.7M20h 1m12392
76Kimi K30.6250$235.66685.5M1.4M19h 49m15211
77GLM-5.3 Flash0.6216$20.18641.6M943k19h 41m15455
78GLM-5.3 Flash0.6062$25.33768.4M1.0M18h 54m171218
79Gemini 3.7 Flash0.5976$41.43380.1M776k20h 1m9444
80Muse Spark 1.30.5582$533.21614.5M1.1M19h 59m15771
81DeepSeek V4 Flash Vision Exp0.5582$23.111453.0M1.8M19h 40m31183
82Muse Spark 1.30.5497$512.38619.2M1.1M19h 59m15981
83Qwen3.8-Max-09020.5325$172.11623.9M2.3M19h 44m155615
84Grok 4.60.5188$107.0399.0M943k6h 25m40219
85Qwen3.8-Max-09020.4966$53.74187.4M939k20h 0m5511
86Muse Spark 1.30.4932$275.581496.0M1.9M19h 49m33613
87Muse Spark 1.30.4932$515.26603.1M1.3M19h 58m14732
88GLM-5.3 Flash0.4777$15.24482.1M673k19h 46m8995
89GLM-5.3 Flash0.4521$17.29524.8M813k19h 25m11485
90Muse Spark 1.30.4384$522.03583.4M1.2M19h 58m14091
91Qwen3.8-Max0.4384$128.73471.1M1.6M19h 41m9652
92DeepSeek V4 Flash Vision Exp0.4212$16.08998.7M1.4M20h 0m21284
93DeepSeek V4 Flash Vision Exp0.3784$22.061380.9M1.8M19h 50m299912
94Gemini 3.7 Flash0.3545$53.22180.3M689k19h 59m5741
95Qwen3.8-Max0.3527$147.05546.0M1.5M19h 49m11092
96DeepSeek V4 Flash Vision Exp0.3253$27.961735.1M2.4M17h 46m379822
97DeepSeek V4 Flash Vision Exp0.3065$23.641484.7M1.9M18h 25m315730
98Qwen3.8-Max0.2894$161.74608.8M1.4M19h 56m14062
99GLM-5.3 Flash0.2860$25.19814.7M1.1M18h 25m19079
100Qwen3.8-Max0.2414$54.19188.0M1.1M20h 0m5971
101Muse Spark 1.20.0445$10.8558.8M321k1h 31m2292
102Muse Spark 1.20.0325$16.8184.3M312k1h 17m3292
103Muse Spark 1.20.0120$23.14130.5M679k1h 19m3953
104Muse Spark 1.20.0051$4.2721.5M175k51m1381
105Inkling0.0017$19.9320.8M47k1h 36m2831
106Inkling0.0000$3.273.4M20k1h 3m982
107Inkling0.0000$13.3613.9M43k1h 28m2271
108Muse Spark 1.20.0000$10.6954.0M468k1h 50m2081
109Inkling0.0000$2.172.2M13k1h 11m801
110Inkling0.0000$9.6410.0M34k1h 28m1692

Vision-only TORCS Racing Bot

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.5284$75.38280.1M713k17h 50m68810
2Claude Opus 5.50.5076$73.95265.4M548k18h 0m55610
3GPT-6 Astra0.4570$770.42373.2M731k19h 37m101312
4Claude Sonnet 5.50.4341$69.62285.7M942k19h 8m6906
5GPT-6 Astra0.3866$1781.91865.7M1.5M19h 55m213325
6Claude Sonnet 5.50.3811$72.87292.1M964k18h 50m7417
7Claude Fable 5.10.3604$65.32119.8M246k14h 32m39916
8Claude Fable 5.10.3524$77.13147.0M311k14h 51m4725
9Claude Opus 50.3059$79.30127.1M413k18h 52m3888
10Claude Sonnet 5.50.3045$106.43367.7M1.1M19h 5m7932
11GPT-6 Astra0.2803$1564.06755.2M1.2M19h 40m185716
12Claude Fable 5.10.2715$77.56137.7M370k10h 32m4267
13Claude Opus 5.50.2616$101.33304.1M515k18h 58m60910
14Claude Fable 5.10.2491$104.18191.5M350k15h 56m5628
15Claude Sonnet 5.50.2220$57.01213.8M846k19h 22m5463
16Claude Sonnet 5.50.2007$76.43316.3M994k19h 1m7517
17Claude Fable 50.1944$174.39145.2M388k18h 8m4478
18Claude Fable 5.10.1812$69.87126.5M304k15h 13m4189
19Claude Opus 50.1513$87.00142.2M403k18h 34m3744
20Claude Haiku 5.50.1276$10.82179.6M761k18h 58m4101
21GPT-5.6 Sol0.1207$165.68160.5M163k9h 38m4167
22Grok 4.60.1206$114.8193.3M882k19h 41m42610
23Qwen3.8-Max0.1078$31.5667.3M1.0M19h 45m4562
24Claude Opus 50.1073$79.88127.0M429k18h 13m3536
25GPT-6 Astra0.1048$823.35394.4M766k19h 59m101814
26GPT-6 Astra0.0879$1737.29826.0M1.5M19h 53m193716
27Gemini 3.8 Flash0.0797$10.3067.6M209k3h 53m3153
28Claude Opus 50.0711$105.95145.9M442k17h 1m3804
29DeepSeek V4 Flash Vision Exp0.0671$3.79218.1M451k16h 2m5914
30Kimi K30.0612$51.38138.7M388k19h 16m4569
31Inkling0.0559$112.11117.1M218k1h 53m8111
32Claude Opus 50.0519$94.80144.0M475k17h 47m4017
33Claude Haiku 5.50.0509$4.7070.8M425k18h 17m2312
34GLM-5.30.0490$52.08118.9M330k18h 59m3542
35Grok 4.70.0456$436.54434.7M834k19h 58m173229
36Claude Haiku 5.50.0451$7.98105.3M596k12h 11m3054
37DeepSeek V4 Flash Vision Exp0.0421$4.04235.7M470k19h 34m6055
38GLM-5.30.0406$79.08158.6M318k18h 36m4068
39Gemini 3.8 Flash0.0405$9.7257.7M157k3h 40m2863
40Muse Spark 1.30.0388$56.56261.0M256k19h 53m8465
41Qwen3.8-Max0.0385$33.8372.9M764k18h 52m4222
42Claude Haiku 5.50.0383$8.88146.9M548k11h 16m3564
43Kimi K30.0382$61.72163.7M377k19h 53m5343
44GLM-5.30.0363$101.89234.7M397k19h 55m4871
45Gemini 3.8 Flash0.0345$10.3785.8M196k4h 25m3402
46Grok 4.60.0335$207.50166.7M1.1M18h 40m69223
47GLM-5.30.0278$99.55248.0M367k18h 54m56314
48Gemini 3.7 Flash0.0235$5.0624.8M145k2h 40m1971
49Qwen3.8-Max0.0216$32.9271.7M721k19h 16m4252
50Kimi K30.0211$44.44114.5M382k20h 0m3861
51Inkling0.0186$4.324.4M39k1h 1m1221
52GLM-5.30.0180$78.52153.1M353k18h 42m3969
53DeepSeek V4 Flash Vision Exp0.0178$3.85221.0M459k11h 59m5557
54Claude Haiku 5.50.0166$6.7195.4M457k13h 37m2722
55Muse Spark 1.30.0144$191.47315.7M497k17h 52m8149
56Kimi K30.0143$59.95154.4M389k20h 1m5072
57Gemini 3.8 Flash0.0136$14.12129.4M330k4h 0m4013
58Muse Spark 1.20.0135$59.82110.7M431k11h 54m3316
59GLM-5.3 Flash0.0132$3.71111.1M281k17h 16m4053
60Inkling0.0129$1.441.4M20k2h 0m841
61GLM-5.3 Flash0.0128$10.01163.4M383k19h 11m5208
62Muse Spark 1.20.0128$52.1470.4M490k14h 49m2894
63Gemini 3.7 Flash0.0127$18.6692.0M417k5h 34m3182
64Grok 4.60.0122$159.04128.5M975k18h 46m56920
65Gemini 3.7 Flash0.0121$11.5163.9M262k4h 49m3102
66Gemini 3.7 Flash0.0118$6.8126.5M177k3h 38m1832
67DeepSeek V4 Flash Vision Exp0.0114$4.73279.3M524k19h 31m6814
68GLM-5.3 Flash0.0065$8.04140.3M327k17h 4m4606
69Qwen3.8-Max0.0061$53.75151.0M965k20h 0m6952
70GLM-5.3 Flash0.0056$7.97164.9M369k18h 14m5506
71Muse Spark 1.20.0051$32.9057.9M354k9h 41m3723
72GLM-5.3 Flash0.0050$8.45168.8M413k16h 34m5195
73Grok 4.60.0043$218.28183.9M1.3M14h 37m75215
74Gemini 3.7 Flash0.0041$7.3932.0M185k3h 17m2131
75Inkling0.0031$5.445.4M67k1h 58m1202
76Muse Spark 1.30.0029$53.07279.6M311k19h 59m98511
77Inkling0.0025$2.422.4M30k2h 1m892
78Qwen3.8-Max-09020.0000†$21.9249.4M903k20h 6m3032
79Muse Spark 1.30.0000†$28.0494.3M152k18h 59m4695
80Gemini 4 Argon0.0000†$81.7158.0M243k8h 45m1803
81DeepSeek V4 Flash Vision Exp0.0000†$2.30127.9M331k19h 43m4543
82Grok 4.70.0000†$129.68133.6M655k14h 50m60311
83Claude Opus 5.50.0000†$60.58240.2M450k18h 1m57111
84Gemini 4 Argon0.0000†$54.6248.6M203k6h 19m1692
85Qwen3.8-Max-09020.0000†$25.5662.5M975k20h 8m4241
86Qwen3.8-Max-09020.0000†$48.14156.8M904k19h 44m5311
87Gemini 4 Argon0.0000†$123.8083.2M286k8h 31m2043
88Claude Fable 50.0000†$81.9461.7M264k17h 37m2932
89GPT-5.6 Sol0.0000†$58.1463.0M111k13h 6m2884
90GPT-5.6 Sol0.0000†$25.7538.4M104k16h 16m2184
91Gemini 4 Argon0.0000†$78.7163.3M288k10h 39m1885
92Grok 4.70.0000†$87.5884.0M222k5h 40m3038
93Grok 4.60.0000†$57.5052.5M468k7h 59m2523
94Claude Fable 50.0000†$92.4270.7M286k18h 32m3135
95Qwen3.8-Max0.0000†$18.0251.8M431k20h 1m4332
96Qwen3.8-Max-09020.0000†$26.8262.8M787k20h 4m3531
97GPT-5.6 Sol0.0000†$51.9957.9M124k4h 17m2776
98Gemini 3.8 Flash0.0000†$7.3051.8M173k3h 58m2884
99GPT-5.6 Sol0.0000†$79.4380.8M113k10h 50m2854
100Qwen3.8-Max-09020.0000†$28.3475.5M595k20h 1m3721
101Kimi K30.0000†$56.92159.4M376k20h 0m5211
102Grok 4.70.0000†$51.7343.4M216k3h 56m1825
103Muse Spark 1.30.0000†$90.6082.5M232k18h 53m4103
104Claude Fable 50.0000†$85.3465.1M256k19h 10m2863
105Gemini 4 Argon0.0000†$96.3987.4M314k10h 9m1983
106Muse Spark 1.20.0000†$35.1065.9M265k9h 20m2293
107Grok 4.70.0000†$353.91323.1M770k19h 55m118513
108Claude Opus 5.50.0000†$51.68197.1M439k16h 52m4747
109Muse Spark 1.20.0000†$27.43124.8M316k10h 1m3854
110Claude Fable 50.0000†$105.0180.0M325k19h 12m3092

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Wan 2.1 on MAX/Mojo

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Claude Opus 5.50.9802$29.4086.6M447k5h 37m21311
2Claude Opus 5.50.9629$25.1276.6M348k3h 15m2079
3GPT-6 Astra0.9623$128.9866.9M202k2h 32m2523
4Claude Opus 5.50.9582$32.70105.1M419k5h 38m2614
5Claude Sonnet 5.50.9507$48.17184.2M875k10h 49m4658
6Claude Opus 5.50.9506$43.10137.3M584k6h 47m2878
7Claude Fable 50.9491$104.4377.8M325k9h 34m2289
8Claude Haiku 5.50.9458$12.55176.8M1.3M10h 31m4172
9Claude Opus 5.50.9418$33.25107.7M418k4h 32m2514
10Claude Sonnet 5.50.9377$25.9498.3M468k4h 54m2464
11Claude Haiku 5.50.9373$12.10180.8M1.1M11h 0m4342
12Claude Sonnet 5.50.9359$40.87157.9M720k8h 10m3726
13Claude Sonnet 5.50.9357$44.27175.5M715k8h 40m4101
14Claude Opus 50.9354$108.05175.6M512k12h 46m38616
15Muse Spark 1.30.9348$88.2491.7M303k11h 17m4092
16Claude Fable 5.10.9331$62.26106.8M367k8h 14m2848
17Claude Fable 50.9315$97.0170.7M318k7h 13m1978
18Claude Fable 5.10.9314$52.8790.3M319k5h 49m2749
19Claude Opus 50.9312$80.95128.6M410k11h 23m3267
20Kimi K30.9307$34.4290.2M306k9h 26m3065
21Claude Fable 50.9285$88.7465.2M284k7h 6m20810
22Claude Opus 50.9268$66.75102.7M380k7h 37m2773
23Claude Fable 50.9266$114.3685.0M368k10h 16m2346
24GPT-5.6 Sol0.9241$103.11107.4M168k5h 28m3698
25Grok 4.70.9226$177.41173.6M635k11h 45m7242
26GPT-6 Astra0.9217$103.1656.8M189k2h 7m2363
27Claude Haiku 5.50.9211$6.92102.7M574k5h 59m2402
28Claude Fable 5.10.9205$68.80118.8M390k9h 16m3236
29Claude Sonnet 5.50.9205$42.18157.9M816k8h 38m4144
30Kimi K30.9196$29.2075.3M345k8h 0m2868
31Claude Fable 5.10.9192$42.8772.2M281k5h 13m2265
32Claude Fable 5.10.9186$55.5395.2M329k8h 32m27910
33Gemini 4 Argon0.9182$55.0365.4M246k4h 0m1712
34Claude Opus 50.9178$120.16201.7M487k16h 10m44012
35GPT-6 Astra0.9173$183.3492.0M226k1h 45m3052
36Claude Fable 50.9155$108.6380.2M355k9h 49m2378
37GPT-6 Astra0.9153$76.8942.2M156k1h 3m1873
38GLM-5.30.9144$51.16175.7M465k14h 14m4612
39GPT-6 Astra0.9128$82.9447.1M162k1h 37m2053
40GLM-5.3 Flash0.9128$8.72173.1M406k16h 39m4892
41Claude Haiku 5.50.9123$8.89128.7M893k9h 43m3762
42Gemini 4 Argon0.9115$102.5378.3M305k5h 26m1812
43Claude Haiku 5.50.9110$9.22144.9M750k8h 8m3336
44GLM-5.30.9094$42.10140.4M401k16h 39m4042
45Grok 4.70.9093$209.09202.2M818k13h 1m8442
46Kimi K30.9090$15.0637.9M188k7h 2m2047
47GLM-5.3 Flash0.9090$7.68170.3M428k17h 42m4766
48GLM-5.30.9087$43.47155.3M374k16h 47m4782
49GPT-5.6 Sol0.9087$34.0444.6M108k4h 5m1999
50Grok 4.60.9085$149.23138.7M1.3M12h 2m5862
51Claude Opus 50.9082$82.70130.5M438k8h 38m3279
52Gemini 4 Argon0.9073$129.59105.1M283k6h 53m2162
53Gemini 4 Argon0.9069$23.6061.0M217k3h 19m1752
54GPT-5.6 Sol0.9062$69.5278.1M124k3h 50m2953
55Grok 4.70.9053$77.0177.8M250k3h 37m3151
56Grok 4.60.9047$29.2330.9M270k3h 12m1581
57Qwen3.8-Max-09020.9041$56.78149.1M2.5M19h 20m4972
58GPT-5.6 Sol0.9014$57.1166.4M129k4h 8m2675
59Grok 4.60.9010$76.5166.4M639k9h 42m2732
60Muse Spark 1.30.9005$242.82232.9M452k19h 26m6281
61Qwen3.8-Max-09020.8953$47.14117.0M1.9M19h 7m4423
62GLM-5.3 Flash0.8916$10.09169.1M376k15h 54m4734
63Kimi K30.8899$31.5184.6M291k12h 22m3483
64GPT-5.6 Sol0.8681$66.0672.8M105k4h 8m2674
65Muse Spark 1.30.4425$115.32111.6M449k19h 59m3851
66Muse Spark 1.30.4417$126.25155.2M591k19h 59m4651
67Qwen3.8-Max0.4407$34.5198.7M1.3M19h 41m4232
68Qwen3.8-Max0.4404$41.1995.2M1.6M20h 1m4271
69DeepSeek V4 Flash Vision Exp0.4396$4.92297.3M464k19h 11m68111
70Muse Spark 1.30.4389$215.78199.3M678k15h 8m50224
71DeepSeek V4 Flash Vision Exp0.4384$3.53204.1M419k17h 55m5623
72DeepSeek V4 Flash Vision Exp0.3550$2.99168.7M386k19h 32m4533
73Gemini 3.8 Flash0.3530$39.56333.6M688k9h 57m9423
74Qwen3.8-Max-09020.3268$45.66130.9M1.8M19h 28m4613
75Qwen3.8-Max-09020.3247$58.55156.5M2.2M19h 45m5123
76Gemini 3.8 Flash0.3004$49.60408.7M919k17h 49m10991
77Gemini 3.8 Flash0.2989$50.71448.6M743k11h 49m11041
78Qwen3.8-Max0.2981$45.25145.8M997k19h 53m5261
79GLM-5.3 Flash0.2971$8.91144.0M373k19h 10m4443
80Kimi K30.2838$85.29208.6M954k19h 56m5583
81DeepSeek V4 Flash Vision Exp0.2720$3.61208.7M436k14h 28m56211
82Grok 4.60.2716$127.41108.5M1.7M19h 30m4644
83DeepSeek V4 Flash Vision Exp0.2506$3.27186.8M413k17h 5m4935
84Grok 4.60.2296$214.90198.0M1.7M19h 41m75913
85Gemini 4 Argon0.1758$81.7398.5M410k6h 12m2591
86GLM-5.30.0945$60.08134.7M351k20h 1m4321
87Qwen3.8-Max0.0664$30.3485.4M1.2M19h 11m3602
88Qwen3.8-Max-09020.0446$62.40166.9M2.3M19h 54m5381
89Inkling0.0429$17.1217.9M30k2h 11m1921
90Inkling0.0404$13.8514.5M23k1h 11m1421
91Gemini 3.7 Flash0.0349$23.63178.6M776k6h 26m5691
92Gemini 3.7 Flash0.0347$27.48166.6M453k6h 47m4381
93Gemini 3.7 Flash0.0331$42.63248.9M797k11h 49m7161
94Muse Spark 1.20.0325$10.9349.7M405k2h 44m1823
95Gemini 3.8 Flash0.0317$65.98570.2M1.4M17h 58m14921
96Gemini 3.7 Flash0.0317$28.92149.4M462k8h 34m3801
97Gemini 3.7 Flash0.0310$36.97183.1M560k8h 49m4831
98Gemini 3.8 Flash0.0309$52.78424.0M773k11h 32m11032
99Inkling0.0305$12.9313.5M35k14m1411
100Muse Spark 1.20.0252$38.37181.5M771k3h 21m48113
101GLM-5.30.0239$77.39173.5M511k19h 46m46411
102Qwen3.8-Max0.0000$50.91123.3M1.9M19h 56m4671
103Muse Spark 1.20.0000$29.55111.8M325k3h 53m3312
104Muse Spark 1.20.0000†$16.0877.6M385k3h 9m2542
105Inkling0.0000$16.0516.8M29k1h 23m1762
106Grok 4.70.0000$218.86185.5M568k19h 57m7918
107Grok 4.70.0000$85.9687.7M287k4h 37m3881
108Muse Spark 1.20.0000$10.8049.7M240k3h 10m2263
109Inkling0.0000$11.4711.9M30k1h 18m1452
110GLM-5.3 Flash0.0000$11.04225.6M397k17h 7m5783

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.