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 | 1.0000 | $34.17 | 49.9M | 378k | 2h 37m | 164 | 6 |
| 2 | Claude Fable 5.1 | 1.0000 | $45.30 | 70.2M | 418k | 4h 0m | 200 | 9 |
| 3 | Claude Fable 5.1 | 1.0000 | $34.22 | 50.9M | 360k | 1h 59m | 159 | 8 |
| 4 | Claude Fable 5.1 | 1.0000 | $43.08 | 67.7M | 379k | 4h 3m | 206 | 11 |
| 5 | Claude Fable 5.1 | 1.0000 | $50.91 | 83.1M | 385k | 3h 9m | 232 | 8 |
| 6 | GPT-5.6 | 0.9807 | $221.16 | 222.7M | 429k | 6h 13m | 691 | 19 |
| 7 | GPT-5.6 | 0.9791 | $78.01 | 86.8M | 272k | 4h 32m | 395 | 2 |
| 8 | GPT-5.6 | 0.9757 | $207.31 | 199.1M | 381k | 7h 23m | 620 | 10 |
| 9 | Gemini 3.7 Flash | 0.9448 | $95.08 | 678.0M | 1.4M | 19h 49m | 1660 | 1 |
| 10 | Gemini 3.7 Flash | 0.9361 | $54.83 | 453.2M | 1.3M | 12h 43m | 1224 | 1 |
| 11 | GPT-5.6 | 0.9339 | $340.15 | 337.0M | 382k | 8h 35m | 789 | 11 |
| 12 | Kimi K3 | 0.9198 | $192.68 | 537.9M | 1.4M | 20h 0m | 1218 | 1 |
| 13 | GLM-5.3 | 0.8650 | $139.71 | 481.8M | 637k | 18h 8m | 859 | 6 |
| 14 | GLM-5.3 | 0.8372 | $111.12 | 401.3M | 867k | 19h 42m | 904 | 10 |
| 15 | Kimi K3 | 0.8313 | $155.97 | 405.9M | 1.5M | 19h 47m | 935 | 3 |
| 16 | GPT-5.6 | 0.7874 | $397.16 | 404.0M | 396k | 8h 54m | 1134 | 7 |
| 17 | Kimi K3 | 0.5265 | $147.65 | 387.7M | 1.4M | 20h 2m | 894 | 1 |
| 18 | Kimi K3 | 0.4229 | $171.33 | 477.1M | 1.3M | 19h 55m | 1130 | 12 |
| 19 | GLM-5.3 | 0.4065 | $133.87 | 385.6M | 660k | 19h 35m | 677 | 3 |
| 20 | Grok 4.6 | 0.3824 | $105.13 | 105.0M | 1.0M | 6h 34m | 490 | 2 |
| 21 | DeepSeek V4 Flash Vision Exp | 0.3599 | $12.71 | 725.7M | 1.6M | 10h 38m | 1614 | 4 |
| 22 | DeepSeek V4 Flash Vision Exp | 0.3164 | $9.48 | 551.4M | 1.2M | 7h 58m | 1228 | 8 |
| 23 | Kimi K3 | 0.2644 | $151.43 | 423.8M | 1.1M | 20h 1m | 928 | 1 |
| 24 | DeepSeek V4 Flash Vision Exp | 0.2513 | $13.44 | 768.2M | 1.8M | 13h 43m | 1760 | 7 |
| 25 | Gemini 3.7 Flash | 0.1248 | $74.81 | 557.5M | 1.1M | 14h 22m | 1217 | 1 |
| 26 | GLM-5.3 | 0.1056 | $134.85 | 474.9M | 964k | 19h 7m | 1105 | 3 |
| 27 | DeepSeek V4 Flash Vision Exp | 0.0143 | $12.56 | 761.2M | 1.2M | 12h 33m | 1627 | 35 |
| 28 | Gemini 3.7 Flash | 0.0087 | $48.94 | 384.1M | 939k | 13h 20m | 1118 | 1 |
| 29 | Muse Spark 1.2 | 0.0000 | $19.14 | 108.5M | 529k | 2h 29m | 348 | 1 |
| 30 | Qwen3.8-Max | 0.0000 | $14.14 | 28.2M | 1.1M | 19h 59m | 169 | 1 |
| 31 | Inkling | 0.0000 | $5.56 | 5.7M | 37k | 1h 16m | 115 | 2 |
| 32 | Inkling | 0.0000 | $5.46 | 5.6M | 34k | 55m | 107 | 2 |
| 33 | Muse Spark 1.2 | 0.0000 | $21.09 | 53.6M | 699k | 3h 48m | 205 | 2 |
| 34 | Muse Spark 1.2 | 0.0000 | $29.46 | 162.8M | 830k | 6h 1m | 404 | 3 |
| 35 | Qwen3.8-Max | 0.0000 | $8.31 | 10.6M | 914k | 19h 59m | 109 | 2 |
| 36 | Inkling | 0.0000 | $5.70 | 5.9M | 22k | 14m | 80 | 2 |
| 37 | Grok 4.6 | 0.0000 | $114.14 | 110.5M | 1.1M | 7h 47m | 492 | 4 |
| 38 | Muse Spark 1.2 | 0.0000 | $27.30 | 88.9M | 859k | 4h 46m | 278 | 1 |
| 39 | Grok 4.6 | 0.0000 | $407.54 | 406.7M | 2.0M | 19h 47m | 1527 | 137 |
| 40 | Grok 4.6 | 0.0000 | $250.10 | 240.1M | 1.8M | 13h 13m | 970 | 43 |
| 41 | Inkling | 0.0000 | $13.81 | 14.4M | 43k | 1h 26m | 175 | 1 |
| 42 | DeepSeek V4 Flash Vision Exp | 0.0000 | $11.64 | 694.6M | 1.3M | 11h 22m | 1413 | 33 |
| 43 | Grok 4.6 | 0.0000 | $233.84 | 217.8M | 2.5M | 19h 53m | 929 | 30 |
| 44 | Muse Spark 1.2 | 0.0000 | $9.51 | 48.0M | 382k | 2h 35m | 213 | 2 |
| 45 | Gemini 3.7 Flash | 0.0000 | $101.50 | 861.0M | 1.8M | 19h 58m | 2092 | 1 |
| 46 | Qwen3.8-Max | 0.0000 | $13.92 | 25.5M | 1.2M | 19h 56m | 167 | 2 |
| 47 | Qwen3.8-Max | 0.0000 | $19.68 | 45.8M | 1.3M | 20h 0m | 211 | 1 |
| 48 | GLM-5.3 | 0.0000 | $113.59 | 400.7M | 1.0M | 18h 31m | 962 | 5 |
| 49 | Qwen3.8-Max | 0.0000 | $10.35 | 13.6M | 1.1M | 19h 57m | 115 | 1 |
| 50 | Inkling | 0.0000 | $6.56 | 6.8M | 25k | 12m | 109 | 6 |