Traces

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

Astronomy Toolkit

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9259$8.2229.7M260k1h 31m1253
2Gemini 4 Carbon0.9046$7.4523.1M248k1h 15m983
3Gemini 4 Carbon0.8999$9.4617.9M258k1h 25m803
4Gemini 4 Carbon0.8058$7.0820.9M281k1h 23m934
5Gemini 4 Carbon0.8058$15.1224.4M286k2h 5m1063

Cranelift Codegen Optimization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.2874$158.76607.0M2.3M20h 0m131631
2Gemini 4 Carbon0.1962$162.25700.7M2.3M19h 47m157634
3Gemini 4 Carbon0.0000$163.59655.6M2.5M19h 55m146736
4Gemini 4 Carbon0.0000$141.98606.5M2.0M19h 53m129826
5Gemini 4 Carbon0.0000$162.00582.9M2.1M19h 37m135133

Crash-Proof Flash Filesystem

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.2838$29.63127.0M596k3h 43m2803
2Gemini 4 Carbon0.1484$32.30139.7M579k5h 1m3273
3Gemini 4 Carbon0.1454$27.17107.9M643k4h 47m2334
4Gemini 4 Carbon0.0173$29.25113.8M646k4h 26m2683
5Gemini 4 Carbon0.0173$29.5197.8M646k5h 9m2483

Dart Style in Haskell

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9611$66.56305.1M1.5M9h 30m74319
2Gemini 4 Carbon0.9539$71.82359.3M1.4M11h 9m82521
3Gemini 4 Carbon0.9419$55.72253.6M1.2M7h 41m60218
4Gemini 4 Carbon0.9296$53.84256.6M1.2M7h 35m61814
5Gemini 4 Carbon0.9267$34.26184.5M928k5h 56m43713

FFmpeg libswscale Optimization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.6845$46.91223.6M1.3M6h 54m49514
2Gemini 4 Carbon0.5793$33.47146.0M1.1M5h 43m34117
3Gemini 4 Carbon0.0000$129.29568.6M3.6M18h 50m122242
4Gemini 4 Carbon0.0000$61.98257.6M1.6M9h 35m57720
5Gemini 4 Carbon0.0000$31.20152.0M948k4h 53m34014

Fitness-Recap Video in Remotion

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.2407$125.51394.8M1.5M19h 28m89926
2Gemini 4 Carbon0.2308$102.07384.6M1.3M20h 1m81334
3Gemini 4 Carbon0.2256$113.52340.8M1.6M19h 47m74733
4Gemini 4 Carbon0.2247$126.19378.0M1.1M14h 22m75830
5Gemini 4 Carbon0.2232$90.68338.4M1.4M19h 15m76138

Flight-Sim Renderer in OpenGL

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9268$112.64321.3M1.4M19h 55m76311
2Gemini 4 Carbon0.8907$78.20248.2M1.1M13h 8m51511
3Gemini 4 Carbon0.8842$58.51166.7M956k13h 14m4088
4Gemini 4 Carbon0.8825$61.99196.8M1.1M12h 30m4397
5Gemini 4 Carbon0.8458$58.27224.6M1.0M11h 25m5078

FrogsGame Post-Training

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9580$32.7826.8M208k19h 58m1223
2Gemini 4 Carbon0.9500$31.3131.7M172k19h 52m1344
3Gemini 4 Carbon0.9100$38.9437.9M210k19h 55m1544
4Gemini 4 Carbon0.8980$36.3029.8M192k19h 58m1316
5Gemini 4 Carbon0.8000$40.2136.7M231k20h 0m1563

Git to Zig

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5929$128.87637.6M2.6M20h 0m138818
2Gemini 4 Carbon0.5770$156.73612.4M2.5M20h 1m135424
3Gemini 4 Carbon0.5651$147.14549.9M2.4M19h 56m128323
4Gemini 4 Carbon0.5598$149.95565.0M2.2M20h 1m125016
5Gemini 4 Carbon0.5322$151.34576.1M2.3M19h 59m128024

Granite Mamba2 Inference Optimization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9288$39.64111.6M938k5h 49m2565
2Gemini 4 Carbon0.9269$24.6149.2M507k3h 3m1255
3Gemini 4 Carbon0.9267$38.6958.6M631k3h 36m1424
4Gemini 4 Carbon0.9260$21.8170.0M515k3h 23m1874
5Gemini 4 Carbon0.8974$39.68102.0M1.2M6h 41m27011

Higgs Uncertainty Inference

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon1.0000$44.3942.7M441k12h 17m1304
2Gemini 4 Carbon1.0000$48.8861.2M497k11h 1m1685
3Gemini 4 Carbon1.0000$45.2954.8M438k12h 40m1425
4Gemini 4 Carbon0.9593$73.0982.0M606k16h 42m2044
5Gemini 4 Carbon0.8560$60.0965.4M511k13h 36m1865

Kolmogorov Audio Compression

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.0807$94.4089.3M634k19h 36m2038
2Gemini 4 Carbon0.0786$101.7879.7M733k19h 56m1597
3Gemini 4 Carbon0.0714$95.6093.0M625k19h 51m21110
4Gemini 4 Carbon0.0692$82.9181.2M552k19h 46m1997
5Gemini 4 Carbon0.0654$95.34111.6M647k19h 19m24211

Lean 4 Kernel Type Checker in Pascal

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon1.0000$16.7653.0M382k2h 4m1332
2Gemini 4 Carbon1.0000$10.6338.3M340k1h 46m1292
3Gemini 4 Carbon1.0000$20.8262.2M414k2h 55m1572
4Gemini 4 Carbon1.0000$24.9159.3M417k3h 35m1612
5Gemini 4 Carbon0.9791$17.6137.8M349k2h 1m1182

libexpat Optimization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5702$17.4476.3M522k2h 14m1864
2Gemini 4 Carbon0.5613$13.7453.5M502k2h 33m1415
3Gemini 4 Carbon0.5291$14.6647.9M485k2h 10m1295
4Gemini 4 Carbon0.4501$11.2049.3M410k2h 38m1464
5Gemini 4 Carbon0.3847$14.6165.7M517k3h 0m1624

Lua Native Compiler

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon1.0000$18.2452.7M358k2h 35m1563
2Gemini 4 Carbon1.0000$23.9272.7M456k2h 53m1673
3Gemini 4 Carbon1.0000$10.8637.2M314k1h 50m1332
4Gemini 4 Carbon0.9528$11.4947.4M307k1h 53m1552
5Gemini 4 Carbon0.9410$9.5933.3M257k1h 26m1203

Machine-Learned Interatomic Potential

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9902$33.7026.5M249k19h 34m1356
2Gemini 4 Carbon0.9857$43.8738.5M333k19h 20m1518
3Gemini 4 Carbon0.9809$36.2929.0M279k19h 28m1245
4Gemini 4 Carbon0.9772$36.9034.1M245k19h 43m1598
5Gemini 4 Carbon0.9668$35.5729.7M255k19h 49m1377

Medium-Range Weather Forecast

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.6348$39.1438.2M277k19h 59m1499
2Gemini 4 Carbon0.6301$42.5140.4M318k19h 49m17110
3Gemini 4 Carbon0.6175$38.4742.8M321k19h 54m1847
4Gemini 4 Carbon0.6098$67.7169.1M303k19h 37m2238
5Gemini 4 Carbon0.5959$59.2280.7M422k19h 46m2499

MEG Speech Decoding

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.3546$110.79105.4M430k19h 42m27811
2Gemini 4 Carbon0.3391$55.8465.8M330k19h 40m2278
3Gemini 4 Carbon0.3341$55.5660.6M332k19h 46m2238
4Gemini 4 Carbon0.3110$74.4777.8M358k19h 50m2435
5Gemini 4 Carbon0.2901$78.67101.9M436k19h 59m2736

MS/MS De Novo Generation

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.1427$37.1756.2M371k18h 24m2106
2Gemini 4 Carbon0.1315$33.3044.8M358k18h 21m1836
3Gemini 4 Carbon0.1265$45.8666.3M400k18h 28m2005
4Gemini 4 Carbon0.1175$37.1351.1M351k18h 31m2006
5Gemini 4 Carbon0.1126$57.88111.8M491k19h 2m2939

Multi-GPU Efficient Finetuning

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.3810$31.5327.6M200k19h 50m1275
2Gemini 4 Carbon0.3810$39.0042.5M193k19h 50m1784
3Gemini 4 Carbon0.3333$35.1531.4M180k19h 44m1365
4Gemini 4 Carbon0.1429$44.5444.2M256k19h 38m1794
5Gemini 4 Carbon0.1190$37.4240.0M214k19h 50m1655

Notebook Compression

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5387$130.03248.7M1.8M19h 48m56216
2Gemini 4 Carbon0.5092$108.09218.0M1.7M19h 51m49516
3Gemini 4 Carbon0.4955$125.20215.7M1.4M19h 27m45815
4Gemini 4 Carbon0.4665$107.43278.5M2.3M20h 2m65521
5Gemini 4 Carbon0.4640$139.93232.8M1.6M20h 4m54117

Optimizer Design

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.3306$63.61105.5M508k19h 32m28112
2Gemini 4 Carbon0.3267$52.49116.9M551k18h 23m30816
3Gemini 4 Carbon0.3033$84.93125.2M506k19h 32m32813
4Gemini 4 Carbon0.2918$89.02127.5M481k19h 9m3036
5Gemini 4 Carbon0.2476$50.6946.6M317k19h 55m1705

PostgreSQL 18 on SQLite

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5769$157.79759.6M2.3M20h 1m172119
2Gemini 4 Carbon0.5495$138.96655.4M2.3M19h 59m150921
3Gemini 4 Carbon0.5440$147.39651.3M2.1M19h 52m146718
4Gemini 4 Carbon0.5330$139.16687.9M2.3M19h 46m158614
5Gemini 4 Carbon0.5275$155.78748.2M2.5M20h 1m164415

Quantum ESPRESSO pw.x in Rust

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.8943$49.66188.3M1.1M8h 17m4414
2Gemini 4 Carbon0.8943$78.28256.0M1.2M12h 11m6075
3Gemini 4 Carbon0.8780$58.29215.8M1.1M7h 25m4925
4Gemini 4 Carbon0.8699$75.46221.0M1.2M9h 56m5345
5Gemini 4 Carbon0.8537$65.85221.2M1.2M7h 55m4804

Qubit Routing

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.8914$42.2455.7M434k7h 6m1666
2Gemini 4 Carbon0.8750$43.4250.0M403k10h 16m16813
3Gemini 4 Carbon0.8722$44.4061.1M483k8h 28m18512
4Gemini 4 Carbon0.8676$39.6347.2M472k7h 44m1538
5Gemini 4 Carbon0.8570$54.0872.6M540k7h 39m19013

Reconnaissance Blind Chess Recovery

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9786$44.1457.0M332k9h 46m1968
2Gemini 4 Carbon0.9643$68.7585.0M399k8h 10m20010
3Gemini 4 Carbon0.9643$57.2570.5M418k14h 24m1988
4Gemini 4 Carbon0.9536$36.2940.2M343k11h 55m1378
5Gemini 4 Carbon0.9429$70.1581.1M395k14h 34m2208

SGLang Inference System Optimization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.0000$125.13534.0M2.2M18h 47m119125
2Gemini 4 Carbon0.0000$107.31433.6M2.0M14h 18m91919
3Gemini 4 Carbon0.0000$113.64517.7M2.3M18h 58m116427
4Gemini 4 Carbon0.0000$146.32601.4M2.3M18h 3m127026
5Gemini 4 Carbon0.0000$128.67547.6M2.2M18h 33m119526

Snooker Prediction

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.6007$47.6198.3M577k5h 39m2416
2Gemini 4 Carbon0.5365$40.62123.2M547k5h 34m2778
3Gemini 4 Carbon0.5355$42.4869.0M425k5h 38m1905
4Gemini 4 Carbon0.4702$74.49187.8M914k9h 55m4587
5Gemini 4 Carbon0.4544$52.60116.1M536k6h 1m2658

SPICE Circuit Simulator in Rust

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9293$55.45239.2M1.7M7h 8m5236
2Gemini 4 Carbon0.9192$73.79296.9M2.2M9h 16m6986
3Gemini 4 Carbon0.9192$57.57230.1M1.6M7h 20m5306
4Gemini 4 Carbon0.9192$49.77221.6M1.5M6h 44m4979
5Gemini 4 Carbon0.9192$90.27376.7M3.0M12h 41m8338

Stepper Music Sequencer GBA

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9872$97.04446.9M2.1M15h 5m97912
2Gemini 4 Carbon0.9708$36.92167.8M841k5h 35m4426
3Gemini 4 Carbon0.9708$43.61230.9M934k8h 4m5589
4Gemini 4 Carbon0.9640$49.83228.0M979k6h 41m4978
5Gemini 4 Carbon0.9392$55.85271.2M1.0M7h 41m5756

Synthetic Music Diarization

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5810$37.6646.7M294k19h 43m2016
2Gemini 4 Carbon0.5627$36.1335.9M284k19h 59m1504
3Gemini 4 Carbon0.5536$40.6043.3M310k18h 47m1616
4Gemini 4 Carbon0.5454$39.1438.1M299k18h 41m1575
5Gemini 4 Carbon0.5444$44.8444.7M333k19h 49m1674

Verilog Simulator in Swift

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9469$16.5668.5M477k2h 50m1904
2Gemini 4 Carbon0.9349$22.8573.1M504k2h 43m1684
3Gemini 4 Carbon0.9315$18.2954.0M458k2h 22m1554
4Gemini 4 Carbon0.9298$17.0269.1M502k2h 53m1744
5Gemini 4 Carbon0.9298$15.0547.7M439k2h 28m1484

Vision-only TORCS Racing Bot

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.5385$91.84101.5M425k18h 27m26613
2Gemini 4 Carbon0.3702$64.0966.9M452k19h 58m2194
3Gemini 4 Carbon0.2900$63.1575.8M441k17h 20m2468
4Gemini 4 Carbon0.2490$60.0376.0M377k17h 4m2505
5Gemini 4 Carbon0.1504$75.4187.9M520k17h 29m2357

Wan 2.1 on MAX/Mojo

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Carbon0.9363$25.0164.2M323k3h 52m1793
2Gemini 4 Carbon0.9187$24.3450.3M315k3h 44m1552
3Gemini 4 Carbon0.9155$31.9652.5M317k4h 35m1603
4Gemini 4 Carbon0.9110$19.7447.1M319k3h 25m1472
5Gemini 4 Carbon0.9097$16.9549.5M262k2h 51m1532