Traces
Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
Kolmogorov Audio Compression
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0462 | $180.50 | 154.3M | 515k | 19h 45m | 631 | 5 |
| 2 | Grok 4.7 | 0.0329 | $52.47 | 42.4M | 229k | 5h 56m | 210 | 12 |
| 3 | Grok 4.7 | 0.0313 | $93.78 | 78.9M | 256k | 12h 4m | 313 | 14 |
| 4 | Grok 4.7 | 0.0218 | $33.81 | 32.7M | 228k | 2h 52m | 171 | 8 |
| 5 | Grok 4.7 | 0.0128 | $49.77 | 44.3M | 205k | 7h 40m | 231 | 6 |
Astronomy Toolkit
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.3076 | $28.45 | 28.6M | 218k | 1h 15m | 142 | 5 |
| 2 | Grok 4.7 | 0.2999 | $23.31 | 23.1M | 224k | 1h 29m | 118 | 3 |
| 3 | Grok 4.7 | 0.0108 | $18.18 | 18.2M | 206k | 1h 1m | 105 | 3 |
| 4 | Grok 4.7 | 0.0075 | $224.04 | 218.5M | 550k | 3h 42m | 699 | 15 |
| 5 | Grok 4.7 | 0.0032 | $13.33 | 14.3M | 178k | 52m | 90 | 2 |
Cranelift Codegen Optimization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0000 | $645.99 | 652.2M | 2.1M | 20h 0m | 2589 | 15 |
| 2 | Grok 4.7 | 0.0000 | $228.14 | 230.9M | 694k | 6h 44m | 948 | 7 |
| 3 | Grok 4.7 | 0.0000 | $477.48 | 483.7M | 1.5M | 16h 55m | 1975 | 20 |
| 4 | Grok 4.7 | 0.0000 | $635.61 | 634.0M | 1.8M | 19h 42m | 2545 | 20 |
| 5 | Grok 4.7 | 0.0000 | $640.87 | 669.7M | 1.8M | 19h 25m | 2877 | 27 |
Dart Style in Haskell
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.7672 | $810.72 | 832.8M | 2.4M | 19h 51m | 3315 | 144 |
| 2 | Grok 4.7 | 0.7101 | $934.33 | 959.7M | 2.7M | 20h 0m | 3786 | 76 |
| 3 | Grok 4.7 | 0.6935 | $819.81 | 827.3M | 2.4M | 19h 30m | 3292 | 79 |
| 4 | Grok 4.7 | 0.6906 | $879.91 | 896.0M | 2.8M | 19h 59m | 3561 | 82 |
| 5 | Grok 4.7 | 0.4324 | $263.14 | 264.6M | 900k | 6h 3m | 996 | 20 |
FFmpeg libswscale Optimization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0717 | $958.45 | 972.7M | 3.5M | 19h 0m | 3810 | 51 |
| 2 | Grok 4.7 | 0.0692 | $75.94 | 76.6M | 393k | 2h 13m | 349 | 5 |
| 3 | Grok 4.7 | 0.0562 | $84.27 | 86.0M | 423k | 2h 12m | 353 | 5 |
| 4 | Grok 4.7 | 0.0482 | $1089.41 | 1092.6M | 3.0M | 15h 42m | 3929 | 49 |
| 5 | Grok 4.7 | 0.0022 | $90.46 | 89.2M | 451k | 3h 23m | 379 | 9 |
Crash-Proof Flash Filesystem
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0806 | $696.28 | 696.9M | 2.0M | 12h 34m | 2584 | 17 |
| 2 | Grok 4.7 | 0.0184 | $312.58 | 313.6M | 1.2M | 9h 0m | 1280 | 10 |
| 3 | Grok 4.7 | 0.0184 | $793.49 | 801.3M | 2.8M | 20h 0m | 3084 | 23 |
| 4 | Grok 4.7 | 0.0173 | $406.03 | 410.3M | 1.5M | 9h 50m | 1624 | 19 |
| 5 | Grok 4.7 | 0.0164 | $349.50 | 343.9M | 1.4M | 11h 51m | 1349 | 8 |
FrogsGame Post-Training
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.4940 | $60.79 | 36.4M | 219k | 19h 41m | 169 | 1 |
| 2 | Grok 4.7 | 0.3640 | $259.38 | 236.3M | 353k | 19h 57m | 795 | 2 |
| 3 | Grok 4.7 | 0.2980 | $90.99 | 63.2M | 209k | 18h 43m | 277 | 2 |
| 4 | Grok 4.7 | 0.2920 | $118.94 | 66.1M | 194k | 19h 26m | 282 | 2 |
| 5 | Grok 4.7 | 0.0460 | $50.68 | 36.5M | 192k | 18h 50m | 196 | 2 |
Stepper Music Sequencer GBA
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.7472 | $628.06 | 649.9M | 2.0M | 11h 13m | 2618 | 63 |
| 2 | Grok 4.7 | 0.6012 | $1385.34 | 1395.4M | 3.2M | 19h 29m | 5064 | 67 |
| 3 | Grok 4.7 | 0.4771 | $380.66 | 393.3M | 1.3M | 7h 10m | 1597 | 32 |
| 4 | Grok 4.7 | 0.4712 | $1073.48 | 1101.7M | 3.6M | 19h 4m | 4513 | 110 |
| 5 | Grok 4.7 | 0.4415 | $440.85 | 450.4M | 1.7M | 8h 48m | 1863 | 19 |
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.2530 | $1242.68 | 1266.7M | 4.0M | 20h 0m | 5068 | 70 |
| 2 | Grok 4.7 | 0.2469 | $910.55 | 936.9M | 2.7M | 19h 58m | 3768 | 53 |
| 3 | Grok 4.7 | 0.2342 | $1107.04 | 1144.5M | 3.0M | 20h 0m | 4638 | 66 |
| 4 | Grok 4.7 | 0.2156 | $741.65 | 767.0M | 2.0M | 19h 54m | 3099 | 73 |
| 5 | Grok 4.7 | 0.1876 | $623.38 | 637.1M | 2.0M | 13h 32m | 2600 | 18 |
Granite Mamba2 Inference Optimization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.8555 | $664.66 | 670.3M | 2.4M | 20h 0m | 2515 | 55 |
| 2 | Grok 4.7 | 0.8303 | $663.28 | 652.6M | 2.1M | 14h 34m | 2345 | 24 |
| 3 | Grok 4.7 | 0.7778 | $748.71 | 746.1M | 3.0M | 20h 0m | 2763 | 23 |
| 4 | Grok 4.7 | 0.7473 | $45.19 | 45.2M | 263k | 1h 21m | 181 | 3 |
| 5 | Grok 4.7 | 0.4410 | $49.65 | 48.3M | 283k | 2h 1m | 184 | 13 |
Higgs Uncertainty Inference
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.7706 | $11.93 | 13.0M | 204k | 1h 11m | 90 | 5 |
| 2 | Grok 4.7 | 0.0000 | $420.44 | 408.4M | 739k | 19h 20m | 1293 | 18 |
| 3 | Grok 4.7 | 0.0000 | $7.84 | 8.3M | 179k | 58m | 63 | 3 |
| 4 | Grok 4.7 | 0.0000 | $17.21 | 17.6M | 220k | 1h 13m | 99 | 5 |
| 5 | Grok 4.7 | 0.0000 | $9.29 | 10.1M | 177k | 1h 2m | 76 | 2 |
SGLang Inference System Optimization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0552 | $802.99 | 801.5M | 2.3M | 19h 22m | 3183 | 24 |
| 2 | Grok 4.7 | 0.0000 | $211.95 | 219.1M | 541k | 7h 14m | 876 | 5 |
| 3 | Grok 4.7 | 0.0000 | $51.59 | 50.1M | 157k | 1h 43m | 212 | 5 |
| 4 | Grok 4.7 | 0.0000 | $100.20 | 104.5M | 326k | 3h 50m | 470 | 5 |
| 5 | Grok 4.7 | 0.0000 | $565.89 | 566.8M | 1.5M | 11h 16m | 2189 | 10 |
Lean 4 Kernel Type Checker in Pascal
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.9589 | $192.69 | 192.9M | 802k | 7h 19m | 790 | 8 |
| 2 | Grok 4.7 | 0.9461 | $478.73 | 472.8M | 1.7M | 19h 19m | 1887 | 5 |
| 3 | Grok 4.7 | 0.9103 | $351.92 | 346.3M | 1.1M | 20h 0m | 1425 | 6 |
| 4 | Grok 4.7 | 0.8682 | $294.16 | 294.8M | 1.1M | 13h 7m | 1229 | 6 |
| 5 | Grok 4.7 | 0.0000 | $418.16 | 407.2M | 1.6M | 18h 42m | 1640 | 7 |
libexpat Optimization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.3527 | $861.01 | 886.1M | 3.3M | 19h 22m | 3633 | 135 |
| 2 | Grok 4.7 | 0.1576 | $386.43 | 383.9M | 880k | 5h 16m | 1277 | 13 |
| 3 | Grok 4.7 | 0.0000 | $77.71 | 79.6M | 493k | 2h 16m | 325 | 4 |
| 4 | Grok 4.7 | 0.0000 | $35.69 | 33.2M | 254k | 1h 17m | 139 | 5 |
| 5 | Grok 4.7 | 0.0000† | $83.03 | 79.6M | 516k | 2h 36m | 314 | 13 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.
Lua Native Compiler
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0000 | $74.24 | 76.4M | 456k | 2h 25m | 373 | 1 |
| 2 | Grok 4.7 | 0.0000 | $23.46 | 23.7M | 161k | 55m | 121 | 1 |
| 3 | Grok 4.7 | 0.0000 | $84.78 | 85.6M | 413k | 2h 11m | 330 | 3 |
| 4 | Grok 4.7 | 0.0000 | $10.18 | 12.5M | 117k | 39m | 81 | 1 |
| 5 | Grok 4.7 | 0.0000 | $15.52 | 17.3M | 144k | 46m | 103 | 1 |
Machine-Learned Interatomic Potential
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.9608 | $60.45 | 36.2M | 244k | 15h 59m | 187 | 2 |
| 2 | Grok 4.7 | 0.9588 | $76.24 | 57.2M | 274k | 16h 2m | 238 | 12 |
| 3 | Grok 4.7 | 0.9549 | $72.03 | 45.6M | 246k | 19h 9m | 215 | 7 |
| 4 | Grok 4.7 | 0.9454 | $102.72 | 67.6M | 289k | 18h 50m | 254 | 8 |
| 5 | Grok 4.7 | 0.0000 | $87.65 | 66.0M | 273k | 12h 6m | 260 | 15 |
Medium-Range Weather Forecast
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.6200 | $170.45 | 150.1M | 788k | 19h 40m | 619 | 21 |
| 2 | Grok 4.7 | 0.5877 | $164.64 | 141.5M | 437k | 18h 53m | 596 | 29 |
| 3 | Grok 4.7 | 0.5339 | $192.06 | 177.7M | 824k | 19h 10m | 758 | 17 |
| 4 | Grok 4.7 | 0.4365 | $22.86 | 23.1M | 216k | 4h 0m | 130 | 3 |
| 5 | Grok 4.7 | 0.4219 | $34.89 | 31.9M | 250k | 3h 58m | 135 | 11 |
MEG Speech Decoding
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.1697 | $27.46 | 25.8M | 199k | 3h 25m | 133 | 5 |
| 2 | Grok 4.7 | 0.0000 | $17.01 | 16.9M | 171k | 3h 5m | 110 | 2 |
| 3 | Grok 4.7 | 0.0000 | $33.74 | 29.5M | 210k | 5h 34m | 157 | 5 |
| 4 | Grok 4.7 | 0.0000 | $9.82 | 11.5M | 148k | 1h 49m | 85 | 2 |
| 5 | Grok 4.7 | 0.0000 | $32.99 | 32.5M | 199k | 5h 31m | 181 | 4 |
Wan 2.1 on MAX/Mojo
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.9226 | $177.41 | 173.6M | 635k | 11h 45m | 724 | 2 |
| 2 | Grok 4.7 | 0.9093 | $209.09 | 202.2M | 818k | 13h 1m | 844 | 2 |
| 3 | Grok 4.7 | 0.9053 | $77.01 | 77.8M | 250k | 3h 37m | 315 | 1 |
| 4 | Grok 4.7 | 0.0000 | $218.86 | 185.5M | 568k | 19h 57m | 791 | 8 |
| 5 | Grok 4.7 | 0.0000 | $85.96 | 87.7M | 287k | 4h 37m | 388 | 1 |
MS/MS De Novo Generation
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.1109 | $12.56 | 12.3M | 170k | 1h 49m | 85 | 2 |
| 2 | Grok 4.7 | 0.1098 | $130.86 | 121.5M | 481k | 15h 47m | 498 | 4 |
| 3 | Grok 4.7 | 0.0968 | $55.01 | 43.9M | 294k | 8h 31m | 190 | 6 |
| 4 | Grok 4.7 | 0.0896 | $57.29 | 42.5M | 256k | 5h 56m | 203 | 6 |
| 5 | Grok 4.7 | 0.0000 | $47.01 | 35.3M | 253k | 6h 31m | 169 | 4 |
Multi-GPU Efficient Finetuning
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0000 | $60.21 | 36.3M | 189k | 18h 34m | 184 | 2 |
| 2 | Grok 4.7 | 0.0000 | $37.89 | 24.1M | 164k | 18h 10m | 140 | 2 |
| 3 | Grok 4.7 | 0.0000 | $29.88 | 18.4M | 159k | 14h 59m | 119 | 3 |
| 4 | Grok 4.7 | 0.0000 | $36.18 | 19.8M | 164k | 20h 0m | 126 | 5 |
| 5 | Grok 4.7 | 0.0000 | $59.65 | 35.5M | 185k | 17h 44m | 170 | 3 |
Notebook Compression
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.2584 | $211.20 | 205.8M | 904k | 13h 1m | 859 | 13 |
| 2 | Grok 4.7 | 0.2464 | $38.17 | 37.7M | 250k | 3h 43m | 192 | 8 |
| 3 | Grok 4.7 | 0.2422 | $40.60 | 41.8M | 253k | 4h 6m | 221 | 11 |
| 4 | Grok 4.7 | 0.2221 | $20.96 | 23.3M | 213k | 3h 13m | 149 | 5 |
| 5 | Grok 4.7 | 0.2015 | $41.06 | 38.3M | 268k | 3h 17m | 188 | 5 |
Flight-Sim Renderer in OpenGL
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.1336 | $487.10 | 480.1M | 1.3M | 20h 1m | 1837 | 77 |
| 2 | Grok 4.7 | 0.1182 | $509.72 | 506.8M | 1.5M | 18h 52m | 2068 | 85 |
| 3 | Grok 4.7 | 0.1138 | $588.60 | 597.8M | 1.8M | 19h 55m | 2409 | 106 |
| 4 | Grok 4.7 | 0.0713 | $540.56 | 547.5M | 1.5M | 19h 14m | 2247 | 102 |
| 5 | Grok 4.7 | 0.0196 | $518.13 | 515.0M | 1.7M | 19h 40m | 2079 | 58 |
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.2867 | $182.37 | 175.0M | 483k | 20h 0m | 744 | 15 |
| 2 | Grok 4.7 | 0.2033 | $279.55 | 260.9M | 639k | 20h 0m | 949 | 17 |
| 3 | Grok 4.7 | 0.0119 | $55.61 | 43.7M | 222k | 7h 51m | 195 | 7 |
| 4 | Grok 4.7 | 0.0000 | $308.24 | 304.6M | 520k | 20h 0m | 1215 | 1 |
| 5 | Grok 4.7 | 0.0000 | $72.65 | 66.7M | 251k | 9h 7m | 265 | 9 |
PostgreSQL 18 on SQLite
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.2747 | $697.58 | 718.7M | 2.2M | 19h 51m | 2979 | 27 |
| 2 | Grok 4.7 | 0.2637 | $767.04 | 780.4M | 2.4M | 18h 58m | 3117 | 30 |
| 3 | Grok 4.7 | 0.2527 | $961.79 | 986.1M | 3.0M | 20h 0m | 3909 | 26 |
| 4 | Grok 4.7 | 0.1978 | $1004.11 | 1036.8M | 3.4M | 20h 0m | 4217 | 22 |
| 5 | Grok 4.7 | 0.0000 | $890.38 | 903.6M | 3.1M | 20h 0m | 3660 | 12 |
Quantum ESPRESSO pw.x in Rust
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.6179 | $248.05 | 251.2M | 1.1M | 11h 32m | 1086 | 16 |
| 2 | Grok 4.7 | 0.4553 | $566.99 | 570.1M | 2.1M | 20h 0m | 2281 | 1 |
| 3 | Grok 4.7 | 0.2764 | $412.96 | 420.2M | 1.8M | 14h 39m | 1779 | 17 |
| 4 | Grok 4.7 | 0.1138 | $593.38 | 588.6M | 2.1M | 20h 0m | 2376 | 1 |
| 5 | Grok 4.7 | 0.0650 | $449.65 | 416.6M | 1.1M | 20h 0m | 1517 | 11 |
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.7346 | $28.62 | 27.0M | 233k | 2h 28m | 119 | 7 |
| 2 | Grok 4.7 | 0.6849 | $35.29 | 35.5M | 255k | 1h 35m | 157 | 10 |
| 3 | Grok 4.7 | 0.6735 | $227.27 | 226.0M | 738k | 19h 38m | 925 | 75 |
| 4 | Grok 4.7 | 0.6585 | $21.77 | 22.6M | 209k | 1h 19m | 122 | 7 |
| 5 | Grok 4.7 | 0.6417 | $24.01 | 24.2M | 210k | 1h 51m | 131 | 4 |
Reconnaissance Blind Chess Recovery
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.8571 | $107.31 | 95.1M | 427k | 11h 56m | 400 | 26 |
| 2 | Grok 4.7 | 0.7821 | $110.91 | 86.8M | 288k | 10h 45m | 306 | 21 |
| 3 | Grok 4.7 | 0.7250 | $43.26 | 41.6M | 230k | 3h 58m | 188 | 3 |
| 4 | Grok 4.7 | 0.5893 | $172.69 | 157.2M | 497k | 15h 0m | 627 | 13 |
| 5 | Grok 4.7 | 0.5607 | $45.18 | 44.4M | 217k | 3h 31m | 197 | 8 |
Fitness-Recap Video in Remotion
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0961 | $439.29 | 445.6M | 1.3M | 9h 16m | 1738 | 103 |
| 2 | Grok 4.7 | 0.0840 | $675.93 | 699.4M | 1.7M | 12h 52m | 2790 | 89 |
| 3 | Grok 4.7 | 0.0491 | $750.66 | 786.8M | 2.0M | 15h 22m | 3238 | 130 |
| 4 | Grok 4.7 | 0.0481 | $814.19 | 833.8M | 1.7M | 19h 58m | 3225 | 109 |
| 5 | Grok 4.7 | 0.0422 | $931.62 | 946.8M | 1.9M | 20h 0m | 3560 | 153 |
Snooker Prediction
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0086 | $81.17 | 79.8M | 486k | 3h 8m | 332 | 5 |
| 2 | Grok 4.7 | 0.0000 | $342.95 | 338.0M | 1.2M | 19h 47m | 1370 | 39 |
| 3 | Grok 4.7 | 0.0000 | $282.03 | 285.1M | 1.2M | 19h 51m | 1191 | 49 |
| 4 | Grok 4.7 | 0.0000 | $61.25 | 64.2M | 387k | 4h 4m | 335 | 5 |
| 5 | Grok 4.7 | 0.0000 | $79.86 | 85.0M | 390k | 6h 4m | 384 | 13 |
SPICE Circuit Simulator in Rust
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.7576 | $721.50 | 746.3M | 2.8M | 15h 40m | 3094 | 16 |
| 2 | Grok 4.7 | 0.7172 | $780.09 | 794.5M | 2.5M | 20h 0m | 3280 | 18 |
| 3 | Grok 4.7 | 0.7071 | $747.81 | 772.9M | 3.1M | 17h 23m | 3267 | 17 |
| 4 | Grok 4.7 | 0.6970 | $807.64 | 821.4M | 3.2M | 17h 39m | 3364 | 44 |
| 5 | Grok 4.7 | 0.6061 | $843.32 | 872.9M | 3.2M | 19h 50m | 3636 | 16 |
Synthetic Music Diarization
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.4597 | $72.67 | 61.2M | 249k | 8h 6m | 249 | 4 |
| 2 | Grok 4.7 | 0.4458 | $66.85 | 49.2M | 265k | 14h 13m | 205 | 10 |
| 3 | Grok 4.7 | 0.4406 | $208.39 | 177.1M | 399k | 19h 30m | 612 | 4 |
| 4 | Grok 4.7 | 0.4284 | $43.87 | 32.2M | 197k | 17h 17m | 180 | 1 |
| 5 | Grok 4.7 | 0.4074 | $96.18 | 79.9M | 265k | 13h 36m | 307 | 8 |
Vision-only TORCS Racing Bot
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.0456 | $436.54 | 434.7M | 834k | 19h 58m | 1732 | 29 |
| 2 | Grok 4.7 | 0.0000† | $129.68 | 133.6M | 655k | 14h 50m | 603 | 11 |
| 3 | Grok 4.7 | 0.0000† | $87.58 | 84.0M | 222k | 5h 40m | 303 | 8 |
| 4 | Grok 4.7 | 0.0000† | $51.73 | 43.4M | 216k | 3h 56m | 182 | 5 |
| 5 | Grok 4.7 | 0.0000† | $353.91 | 323.1M | 770k | 19h 55m | 1185 | 13 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.
Verilog Simulator in Swift
task page →5 runs · indexed 2026-09-22| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|
| 1 | Grok 4.7 | 0.8853 | $200.79 | 205.0M | 994k | 5h 44m | 853 | 1 |
| 2 | Grok 4.7 | 0.8784 | $244.06 | 246.8M | 1.1M | 15h 21m | 1005 | 27 |
| 3 | Grok 4.7 | 0.8596 | $839.06 | 861.8M | 2.3M | 19h 58m | 3507 | 37 |
| 4 | Grok 4.7 | 0.8510 | $180.74 | 176.1M | 878k | 5h 58m | 658 | 4 |
| 5 | Grok 4.7 | 0.8476 | $334.11 | 341.6M | 1.2M | 11h 19m | 1457 | 47 |