Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.8444 | $169.75 | 555.3M | 2.2M | 12h 14m | 1230 | 42 |
| 2 | Claude Fable 5.1 | 0.8080 | $283.04 | 487.0M | 1.6M | 13h 9m | 1070 | 46 |
| 3 | Claude Sonnet 5.5 | 0.5593 | $210.44 | 829.8M | 3.5M | 18h 18m | 1662 | 32 |
| 4 | Claude Fable 5.1 | 0.5509 | $202.06 | 343.4M | 1.3M | 9h 13m | 819 | 28 |
| 5 | Claude Sonnet 5.5 | 0.5128 | $191.15 | 731.8M | 3.5M | 16h 45m | 1549 | 18 |
| 6 | Claude Fable 5.1 | 0.5106 | $148.93 | 254.0M | 906k | 6h 11m | 641 | 18 |
| 7 | Claude Fable 5 | 0.3296 | $651.27 | 511.9M | 1.9M | 17h 29m | 1099 | 44 |
| 8 | GPT-6 Astra | 0.2755 | $169.85 | 82.4M | 307k | 2h 7m | 290 | 7 |
| 9 | Claude Opus 5 | 0.2730 | $386.74 | 584.2M | 2.5M | 17h 26m | 1236 | 48 |
| 10 | Claude Opus 5 | 0.2685 | $323.38 | 505.1M | 1.9M | 18h 50m | 1055 | 36 |
| 11 | Claude Haiku 5.5 | 0.2461 | $32.33 | 512.1M | 2.4M | 8h 34m | 1174 | 9 |
| 12 | Claude Fable 5 | 0.2400 | $694.93 | 559.7M | 1.8M | 18h 56m | 1226 | 65 |
| 13 | Claude Opus 5 | 0.2348 | $359.20 | 577.0M | 1.9M | 15h 26m | 1190 | 24 |
| 14 | Claude Fable 5 | 0.2293 | $457.04 | 364.2M | 1.2M | 18h 33m | 758 | 37 |
| 15 | Claude Haiku 5.5 | 0.2204 | $29.73 | 450.8M | 2.6M | 7h 6m | 996 | 2 |
| 16 | Claude Opus 5 | 0.2127 | $514.92 | 809.2M | 2.9M | 17h 33m | 1760 | 45 |
| 17 | GPT-6 Astra | 0.2021 | $313.12 | 153.5M | 377k | 2h 54m | 458 | 9 |
| 18 | GPT-6 Astra | 0.1983 | $306.45 | 149.1M | 351k | 2h 48m | 444 | 8 |
| 19 | Claude Opus 5 | 0.1899 | $481.68 | 774.7M | 2.5M | 14h 53m | 1592 | 54 |
| 20 | GLM-5.3 | 0.1752 | $226.40 | 818.4M | 2.0M | 19h 33m | 1884 | 18 |
| 21 | GPT-6 Astra | 0.1741 | $262.36 | 125.2M | 349k | 2h 37m | 379 | 6 |
| 22 | Claude Fable 5 | 0.1712 | $501.72 | 411.4M | 1.2M | 18h 49m | 877 | 42 |
| 23 | Claude Haiku 5.5 | 0.1587 | $30.27 | 466.6M | 2.5M | 11h 4m | 1072 | 17 |
| 24 | Gemini 4 Argon | 0.1572 | $160.32 | 346.6M | 1.9M | 11h 31m | 765 | 13 |
| 25 | Claude Fable 5 | 0.1436 | $530.26 | 432.3M | 1.3M | 19h 40m | 864 | 28 |
| 26 | GLM-5.3 | 0.1410 | $148.35 | 524.2M | 1.7M | 16h 26m | 1303 | 8 |
| 27 | GLM-5.3 | 0.1369 | $139.76 | 505.8M | 1.2M | 11h 14m | 1097 | 9 |
| 28 | Claude Fable 5.1 | 0.1368 | $219.11 | 385.2M | 1.1M | 10h 27m | 835 | 22 |
| 29 | Muse Spark 1.3 | 0.1277 | $499.70 | 617.7M | 951k | 19h 17m | 1401 | 24 |
| 30 | GLM-5.3 Flash | 0.1268 | $16.00 | 489.1M | 1.2M | 13h 53m | 1179 | 110 |
| 31 | Kimi K3 | 0.1260 | $127.79 | 342.6M | 1.2M | 13h 59m | 827 | 13 |
| 32 | Kimi K3 | 0.1252 | $211.22 | 606.6M | 1.4M | 19h 43m | 1382 | 3 |
| 33 | GLM-5.3 | 0.1231 | $175.55 | 619.5M | 1.7M | 16h 47m | 1509 | 8 |
| 34 | Claude Opus 5.5 | 0.1224 | $83.47 | 264.7M | 1.1M | 5h 11m | 549 | 14 |
| 35 | Claude Opus 5.5 | 0.1185 | $175.12 | 575.5M | 2.3M | 11h 51m | 1203 | 46 |
| 36 | GPT-6 Astra | 0.1179 | $275.12 | 132.2M | 355k | 2h 35m | 396 | 6 |
| 37 | Muse Spark 1.3 | 0.1028 | $438.57 | 557.6M | 1.0M | 16h 30m | 1340 | 23 |
| 38 | Claude Sonnet 5.5 | 0.1012 | $189.51 | 720.9M | 3.5M | 18h 17m | 1538 | 35 |
| 39 | Muse Spark 1.3 | 0.1003 | $186.76 | 239.3M | 502k | 7h 59m | 559 | 14 |
| 40 | Muse Spark 1.3 | 0.0996 | $157.06 | 200.2M | 465k | 6h 34m | 504 | 12 |
| 41 | GLM-5.3 Flash | 0.0819 | $11.44 | 312.2M | 1.0M | 11h 47m | 786 | 2 |
| 42 | Kimi K3 | 0.0799 | $127.97 | 356.2M | 1.1M | 15h 4m | 914 | 11 |
| 43 | GLM-5.3 | 0.0783 | $177.95 | 625.3M | 1.7M | 17h 1m | 1420 | 8 |
| 44 | Muse Spark 1.3 | 0.0779 | $279.58 | 336.6M | 595k | 9h 26m | 688 | 17 |
| 45 | Claude Haiku 5.5 | 0.0742 | $11.46 | 167.4M | 1.1M | 3h 2m | 421 | 4 |
| 46 | GLM-5.3 Flash | 0.0721 | $12.54 | 348.2M | 1.1M | 9h 45m | 838 | 4 |
| 47 | Grok 4.7 | 0.0717 | $958.45 | 972.7M | 3.5M | 19h 0m | 3810 | 51 |
| 48 | GLM-5.3 Flash | 0.0710 | $14.74 | 418.0M | 1.0M | 13h 2m | 963 | 6 |
| 49 | Claude Sonnet 5.5 | 0.0703 | $164.01 | 627.4M | 3.0M | 15h 19m | 1268 | 23 |
| 50 | Grok 4.7 | 0.0692 | $75.94 | 76.6M | 393k | 2h 13m | 349 | 5 |
| 51 | DeepSeek V4 Flash Vision Exp | 0.0668 | $8.52 | 493.3M | 1.0M | 6h 44m | 1095 | 8 |
| 52 | Kimi K3 | 0.0639 | $138.03 | 382.3M | 1.1M | 17h 32m | 902 | 2 |
| 53 | DeepSeek V4 Flash Vision Exp | 0.0636 | $9.11 | 528.7M | 1.1M | 6h 10m | 1172 | 5 |
| 54 | DeepSeek V4 Flash Vision Exp | 0.0602 | $13.77 | 800.3M | 1.6M | 9h 14m | 1831 | 19 |
| 55 | GLM-5.3 Flash | 0.0591 | $10.52 | 294.6M | 1.1M | 15h 39m | 768 | 1 |
| 56 | Grok 4.7 | 0.0562 | $84.27 | 86.0M | 423k | 2h 12m | 353 | 5 |
| 57 | DeepSeek V4 Flash Vision Exp | 0.0483 | $9.39 | 554.1M | 1.0M | 5h 54m | 1197 | 16 |
| 58 | Grok 4.7 | 0.0482 | $1089.41 | 1092.6M | 3.0M | 15h 42m | 3929 | 49 |
| 59 | Claude Sonnet 5.5 | 0.0471 | $76.69 | 272.4M | 1.7M | 6h 51m | 612 | 9 |
| 60 | Claude Opus 5.5 | 0.0441 | $106.98 | 317.9M | 1.6M | 6h 52m | 693 | 18 |
| 61 | Gemini 3.8 Flash | 0.0421 | $22.33 | 232.8M | 629k | 2h 36m | 656 | 8 |
| 62 | Qwen3.8-Max | 0.0373 | $86.44 | 286.2M | 2.3M | 17h 43m | 706 | 6 |
| 63 | Grok 4.6 | 0.0360 | $419.25 | 404.2M | 2.4M | 19h 56m | 1517 | 114 |
| 64 | Qwen3.8-Max | 0.0181 | $64.05 | 193.9M | 2.4M | 18h 48m | 555 | 1 |
| 65 | Gemini 3.7 Flash | 0.0125 | $20.83 | 184.0M | 617k | 2h 35m | 524 | 2 |
| 66 | Qwen3.8-Max | 0.0053 | $46.03 | 124.6M | 2.3M | 19h 58m | 424 | 1 |
| 67 | Gemini 3.7 Flash | 0.0032 | $19.94 | 167.8M | 795k | 2h 4m | 496 | 7 |
| 68 | Grok 4.7 | 0.0022 | $90.46 | 89.2M | 451k | 3h 23m | 379 | 9 |
| 69 | Grok 4.6 | 0.0000 | $1121.42 | 1126.0M | 2.4M | 18h 11m | 3693 | 434 |
| 70 | Muse Spark 1.2 | 0.0000 | $15.42 | 90.0M | 327k | 41m | 286 | 2 |
| 71 | Grok 4.6 | 0.0000 | $68.40 | 59.6M | 603k | 3h 50m | 229 | 4 |
| 72 | Muse Spark 1.2 | 0.0000 | $16.97 | 85.6M | 384k | 1h 38m | 227 | 4 |
| 73 | Gemini 3.8 Flash | 0.0000 | $23.73 | 247.4M | 548k | 2h 37m | 674 | 3 |
| 74 | Claude Fable 5.1 | 0.0000 | $217.24 | 363.8M | 1.5M | 10h 22m | 893 | 27 |
| 75 | Gemini 4 Argon | 0.0000 | $156.84 | 296.0M | 1.6M | 9h 55m | 668 | 11 |
| 76 | Gemini 4 Argon | 0.0000 | $106.17 | 273.4M | 1.3M | 8h 28m | 605 | 17 |
| 77 | Qwen3.8-Max | 0.0000 | $54.69 | 158.2M | 2.4M | 18h 58m | 475 | 1 |
| 78 | Grok 4.6 | 0.0000 | $132.56 | 129.2M | 778k | 5h 28m | 562 | 27 |
| 79 | Inkling | 0.0000 | $11.24 | 11.7M | 27k | 1h 20m | 165 | 2 |
| 80 | Inkling | 0.0000 | $15.45 | 16.1M | 35k | 22m | 188 | 2 |
| 81 | Gemini 3.8 Flash | 0.0000 | $19.00 | 192.6M | 496k | 2h 5m | 536 | 4 |
| 82 | Qwen3.8-Max-0902 | 0.0000 | $39.61 | 68.0M | 3.6M | 20h 1m | 275 | 1 |
| 83 | Qwen3.8-Max | 0.0000 | $30.12 | 66.3M | 2.1M | 19h 55m | 298 | 1 |
| 84 | Inkling | 0.0000 | $39.66 | 41.4M | 77k | 41m | 354 | 2 |
| 85 | Gemini 3.7 Flash | 0.0000 | $25.27 | 228.2M | 1.1M | 2h 14m | 655 | 5 |
| 86 | GPT-5.6 Sol | 0.0000 | $66.82 | 75.1M | 179k | 1h 59m | 318 | 8 |
| 87 | Gemini 3.8 Flash | 0.0000 | $31.46 | 339.3M | 663k | 5h 43m | 881 | 17 |
| 88 | Qwen3.8-Max-0902 | 0.0000 | $44.84 | 72.8M | 3.4M | 20h 2m | 345 | 1 |
| 89 | Inkling | 0.0000 | $15.51 | 16.2M | 36k | 32m | 190 | 1 |
| 90 | Muse Spark 1.2 | 0.0000 | $11.90 | 64.7M | 340k | 1h 14m | 223 | 2 |
| 91 | GPT-5.6 Sol | 0.0000 | $78.43 | 84.8M | 190k | 2h 4m | 348 | 5 |
| 92 | Grok 4.6 | 0.0000 | $380.75 | 368.6M | 1.8M | 11h 52m | 1370 | 67 |
| 93 | Muse Spark 1.2 | 0.0000 | $35.70 | 203.8M | 978k | 3h 29m | 468 | 8 |
| 94 | Claude Haiku 5.5 | 0.0000 | $13.45 | 205.4M | 1.1M | 2h 38m | 488 | 3 |
| 95 | GPT-5.6 Sol | 0.0000 | $123.31 | 124.9M | 233k | 2h 12m | 422 | 3 |
| 96 | Kimi K3 | 0.0000 | $171.14 | 500.1M | 1.1M | 19h 41m | 1175 | 47 |
| 97 | Qwen3.8-Max-0902 | 0.0000 | $51.17 | 115.3M | 3.5M | 20h 1m | 358 | 1 |
| 98 | Claude Opus 5.5 | 0.0000 | $168.91 | 529.9M | 2.4M | 15h 41m | 1150 | 37 |
| 99 | GPT-5.6 Sol | 0.0000 | $76.67 | 86.4M | 186k | 3h 5m | 369 | 10 |
| 100 | Gemini 4 Argon | 0.0000 | $58.88 | 167.7M | 1.1M | 5h 59m | 405 | 7 |
| 101 | Qwen3.8-Max-0902 | 0.0000 | $43.43 | 82.1M | 3.6M | 20h 1m | 306 | 1 |
| 102 | DeepSeek V4 Flash Vision Exp | 0.0000 | $12.34 | 718.0M | 1.4M | 8h 32m | 1678 | 16 |
| 103 | GPT-5.6 Sol | 0.0000 | $117.96 | 120.8M | 233k | 3h 42m | 405 | 8 |
| 104 | Inkling | 0.0000 | $11.17 | 11.6M | 27k | 16m | 167 | 1 |
| 105 | Qwen3.8-Max-0902 | 0.0000 | $72.15 | 209.7M | 3.0M | 19h 38m | 543 | 1 |
| 106 | Gemini 4 Argon | 0.0000 | $190.93 | 224.2M | 1.2M | 7h 43m | 531 | 8 |
| 107 | Gemini 3.8 Flash | 0.0000 | $22.37 | 231.7M | 581k | 2h 9m | 683 | 12 |
| 108 | Gemini 3.7 Flash | 0.0000 | $16.99 | 131.7M | 937k | 2h 45m | 448 | 6 |
| 109 | Muse Spark 1.2 | 0.0000 | $27.98 | 159.1M | 568k | 1h 40m | 345 | 2 |
| 110 | Gemini 3.7 Flash | 0.0000 | $44.74 | 251.9M | 922k | 8h 1m | 758 | 6 |