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 Fable 5.1 | 0.9332 | $262.30 | 478.6M | 947k | 9h 23m | 1148 | 17 |
| 2 | Claude Fable 5.1 | 0.9315 | $216.99 | 391.4M | 878k | 7h 55m | 966 | 6 |
| 3 | Claude Fable 5.1 | 0.9195 | $211.66 | 382.5M | 840k | 9h 40m | 989 | 17 |
| 4 | Claude Fable 5.1 | 0.9161 | $266.36 | 483.7M | 1.0M | 10h 14m | 1167 | 34 |
| 5 | Claude Fable 5.1 | 0.9092 | $168.96 | 308.4M | 606k | 6h 47m | 586 | 10 |
| 6 | GPT-5.6 | 0.8853 | $427.16 | 420.2M | 394k | 14h 37m | 921 | 9 |
| 7 | GPT-5.6 | 0.8596 | $271.89 | 260.9M | 315k | 4h 56m | 650 | 5 |
| 8 | GPT-5.6 | 0.8493 | $335.11 | 326.9M | 349k | 4h 23m | 746 | 9 |
| 9 | Kimi K3 | 0.8373 | $248.18 | 704.4M | 1.6M | 20h 0m | 1636 | 11 |
| 10 | GPT-5.6 | 0.8339 | $184.09 | 180.1M | 273k | 4h 24m | 480 | 6 |
| 11 | Gemini 3.7 Flash | 0.8305 | $103.65 | 1018.6M | 2.0M | 19h 58m | 2418 | 1 |
| 12 | Gemini 3.7 Flash | 0.8288 | $74.39 | 745.3M | 2.1M | 17h 44m | 1828 | 1 |
| 13 | Grok 4.6 | 0.8253 | $223.65 | 211.2M | 1.9M | 12h 53m | 884 | 31 |
| 14 | GLM-5.3 | 0.8236 | $236.70 | 879.4M | 1.3M | 20h 1m | 1924 | 11 |
| 15 | GPT-5.6 | 0.8236 | $181.11 | 176.3M | 277k | 4h 52m | 476 | 3 |
| 16 | Gemini 3.7 Flash | 0.8202 | $75.29 | 725.4M | 1.4M | 19h 4m | 1651 | 2 |
| 17 | GLM-5.3 | 0.8151 | $195.25 | 722.0M | 1.1M | 19h 28m | 1706 | 10 |
| 18 | Grok 4.6 | 0.8116 | $347.28 | 325.2M | 2.2M | 19h 55m | 1222 | 56 |
| 19 | GLM-5.3 | 0.7757 | $229.93 | 817.6M | 1.1M | 19h 47m | 1800 | 19 |
| 20 | GLM-5.3 | 0.7723 | $247.89 | 875.5M | 1.2M | 19h 55m | 1804 | 17 |
| 21 | Kimi K3 | 0.7551 | $141.93 | 387.6M | 1.1M | 20h 1m | 1009 | 1 |
| 22 | Qwen3.8-Max | 0.7551 | $162.17 | 597.6M | 1.8M | 19h 37m | 1491 | 1 |
| 23 | GLM-5.3 | 0.7551 | $285.37 | 1061.6M | 1.4M | 19h 46m | 2367 | 23 |
| 24 | Grok 4.6 | 0.7517 | $518.10 | 508.9M | 2.5M | 19h 53m | 1842 | 50 |
| 25 | Kimi K3 | 0.7175 | $256.44 | 747.8M | 1.5M | 20h 1m | 1669 | 2 |
| 26 | Grok 4.6 | 0.6901 | $168.65 | 160.9M | 1.6M | 9h 35m | 691 | 25 |
| 27 | Kimi K3 | 0.6849 | $265.41 | 774.0M | 1.6M | 19h 54m | 1682 | 2 |
| 28 | Kimi K3 | 0.6250 | $235.66 | 685.5M | 1.4M | 19h 49m | 1521 | 1 |
| 29 | Gemini 3.7 Flash | 0.5976 | $41.43 | 380.1M | 776k | 20h 1m | 944 | 4 |
| 30 | DeepSeek V4 Flash Vision Exp | 0.5582 | $23.11 | 1453.0M | 1.8M | 19h 40m | 3118 | 3 |
| 31 | Grok 4.6 | 0.5188 | $107.03 | 99.0M | 943k | 6h 25m | 402 | 19 |
| 32 | Qwen3.8-Max | 0.4384 | $128.73 | 471.1M | 1.6M | 19h 41m | 965 | 2 |
| 33 | DeepSeek V4 Flash Vision Exp | 0.4212 | $16.08 | 998.7M | 1.4M | 20h 0m | 2128 | 4 |
| 34 | DeepSeek V4 Flash Vision Exp | 0.3784 | $22.06 | 1380.9M | 1.8M | 19h 50m | 2999 | 12 |
| 35 | Gemini 3.7 Flash | 0.3545 | $53.22 | 180.3M | 689k | 19h 59m | 574 | 1 |
| 36 | Qwen3.8-Max | 0.3527 | $147.05 | 546.0M | 1.5M | 19h 49m | 1109 | 2 |
| 37 | DeepSeek V4 Flash Vision Exp | 0.3253 | $27.96 | 1735.1M | 2.4M | 17h 46m | 3798 | 22 |
| 38 | DeepSeek V4 Flash Vision Exp | 0.3065 | $23.64 | 1484.7M | 1.9M | 18h 25m | 3157 | 30 |
| 39 | Qwen3.8-Max | 0.2894 | $161.74 | 608.8M | 1.4M | 19h 56m | 1406 | 2 |
| 40 | Qwen3.8-Max | 0.2414 | $54.19 | 188.0M | 1.1M | 20h 0m | 597 | 1 |
| 41 | Muse Spark 1.2 | 0.0445 | $10.85 | 58.8M | 321k | 1h 31m | 229 | 2 |
| 42 | Muse Spark 1.2 | 0.0325 | $16.81 | 84.3M | 312k | 1h 17m | 329 | 2 |
| 43 | Muse Spark 1.2 | 0.0120 | $23.14 | 130.5M | 679k | 1h 19m | 395 | 3 |
| 44 | Muse Spark 1.2 | 0.0051 | $4.27 | 21.5M | 175k | 51m | 138 | 1 |
| 45 | Inkling | 0.0017 | $19.93 | 20.8M | 47k | 1h 36m | 283 | 1 |
| 46 | Inkling | 0.0000 | $3.27 | 3.4M | 20k | 1h 3m | 98 | 2 |
| 47 | Inkling | 0.0000 | $13.36 | 13.9M | 43k | 1h 28m | 227 | 1 |
| 48 | Muse Spark 1.2 | 0.0000 | $10.69 | 54.0M | 468k | 1h 50m | 208 | 1 |
| 49 | Inkling | 0.0000 | $2.17 | 2.2M | 13k | 1h 11m | 80 | 1 |
| 50 | Inkling | 0.0000 | $9.64 | 10.0M | 34k | 1h 28m | 169 | 2 |