Traces

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

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.