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 | 0.5674 | $350.25 | 628.4M | 1.5M | 16h 3m | 1456 | 82 |
| 2 | Claude Fable 5.1 | 0.5395 | $313.80 | 554.2M | 1.5M | 11h 26m | 1289 | 34 |
| 3 | Claude Fable 5.1 | 0.4885 | $375.68 | 676.2M | 1.5M | 17h 3m | 1505 | 50 |
| 4 | Claude Fable 5.1 | 0.4469 | $289.07 | 503.7M | 1.5M | 13h 41m | 1156 | 50 |
| 5 | GPT-5.6 | 0.3847 | $146.13 | 140.6M | 311k | 2h 25m | 439 | 7 |
| 6 | GPT-5.6 | 0.3225 | $67.06 | 75.3M | 223k | 1h 44m | 326 | 9 |
| 7 | GPT-5.6 | 0.3025 | $18.35 | 26.1M | 127k | 53m | 144 | 4 |
| 8 | Claude Fable 5.1 | 0.2880 | $179.04 | 308.9M | 1.0M | 10h 29m | 755 | 12 |
| 9 | GPT-5.6 | 0.2868 | $49.11 | 53.9M | 193k | 1h 32m | 238 | 5 |
| 10 | GPT-5.6 | 0.2751 | $110.05 | 104.7M | 243k | 2h 24m | 350 | 7 |
| 11 | Gemini 3.7 Flash | 0.2399 | $41.35 | 394.7M | 960k | 4h 30m | 1009 | 6 |
| 12 | GLM-5.3 | 0.2372 | $181.79 | 673.8M | 1.1M | 8h 14m | 1501 | 3 |
| 13 | GLM-5.3 | 0.2303 | $183.58 | 670.1M | 1.1M | 9h 50m | 1460 | 18 |
| 14 | GLM-5.3 | 0.1823 | $327.58 | 1209.3M | 1.8M | 18h 23m | 2635 | 46 |
| 15 | Kimi K3 | 0.1778 | $238.01 | 679.3M | 1.8M | 19h 52m | 1588 | 83 |
| 16 | GLM-5.3 | 0.1583 | $236.28 | 865.5M | 1.6M | 18h 53m | 1991 | 34 |
| 17 | Gemini 3.7 Flash | 0.1572 | $41.30 | 358.7M | 785k | 6h 1m | 899 | 5 |
| 18 | Gemini 3.7 Flash | 0.1555 | $24.69 | 216.5M | 877k | 2h 56m | 624 | 2 |
| 19 | Kimi K3 | 0.1513 | $169.56 | 484.2M | 1.2M | 19h 34m | 1155 | 16 |
| 20 | Grok 4.6 | 0.1479 | $150.76 | 148.7M | 804k | 4h 11m | 580 | 26 |
| 21 | Grok 4.6 | 0.1393 | $108.10 | 108.1M | 736k | 4h 5m | 435 | 11 |
| 22 | Kimi K3 | 0.1288 | $173.14 | 509.0M | 1.1M | 13h 23m | 1149 | 28 |
| 23 | Grok 4.6 | 0.1022 | $79.42 | 75.8M | 516k | 2h 56m | 273 | 7 |
| 24 | DeepSeek V4 Flash Vision Exp | 0.0891 | $17.04 | 1034.3M | 1.6M | 6h 42m | 2273 | 6 |
| 25 | DeepSeek V4 Flash Vision Exp | 0.0545 | $16.46 | 992.0M | 1.7M | 6h 43m | 2222 | 11 |
| 26 | Muse Spark 1.2 | 0.0000 | $40.00 | 150.5M | 651k | 3h 23m | 388 | 3 |
| 27 | Muse Spark 1.2 | 0.0000 | $41.66 | 132.7M | 956k | 3h 49m | 473 | 3 |
| 28 | Inkling | 0.0000 | $23.47 | 24.5M | 46k | 39m | 359 | 2 |
| 29 | Muse Spark 1.2 | 0.0000 | $16.54 | 87.9M | 378k | 1h 23m | 309 | 3 |
| 30 | Qwen3.8-Max | 0.0000 | $21.15 | 36.8M | 1.9M | 20h 0m | 260 | — |
| 31 | Inkling | 0.0000 | $3.70 | 3.7M | 39k | 18m | 85 | 2 |
| 32 | Qwen3.8-Max | 0.0000 | $16.28 | 22.3M | 1.7M | 19h 46m | 202 | — |
| 33 | Gemini 3.7 Flash | 0.0000 | $33.92 | 328.7M | 960k | 2h 58m | 810 | 20 |
| 34 | DeepSeek V4 Flash Vision Exp | 0.0000 | $13.51 | 827.8M | 1.3M | 5h 43m | 1720 | 13 |
| 35 | DeepSeek V4 Flash Vision Exp | 0.0000 | $21.93 | 1323.6M | 2.2M | 8h 50m | 3095 | 7 |
| 36 | Gemini 3.7 Flash | 0.0000 | $29.56 | 325.1M | 599k | 2h 10m | 830 | 2 |
| 37 | DeepSeek V4 Flash Vision Exp | 0.0000 | $33.36 | 1965.0M | 3.8M | 19h 31m | 4102 | 48 |
| 38 | Kimi K3 | 0.0000 | $214.44 | 584.8M | 1.8M | 20h 0m | 1459 | 1 |
| 39 | Inkling | 0.0000 | $18.36 | 19.0M | 75k | 47m | 251 | 4 |
| 40 | Qwen3.8-Max | 0.0000 | $19.23 | 33.9M | 1.7M | 19h 53m | 233 | 1 |
| 41 | Grok 4.6 | 0.0000 | $93.77 | 99.5M | 677k | 3h 26m | 435 | 10 |
| 42 | Muse Spark 1.2 | 0.0000 | $39.83 | 172.4M | 582k | 3h 18m | 559 | 6 |
| 43 | Inkling | 0.0000 | $3.58 | 3.6M | 31k | 16m | 74 | 2 |
| 44 | Qwen3.8-Max | 0.0000 | $25.12 | 46.8M | 2.2M | 19h 55m | 301 | — |
| 45 | Muse Spark 1.2 | 0.0000 | $32.92 | 157.9M | 806k | 3h 52m | 344 | 3 |
| 46 | Grok 4.6 | 0.0000 | $71.78 | 70.3M | 399k | 1h 58m | 277 | 5 |
| 47 | Qwen3.8-Max | 0.0000 | $13.06 | 14.1M | 1.6M | 19h 35m | 156 | — |
| 48 | Inkling | 0.0000 | $3.11 | 3.2M | 24k | 13m | 82 | 3 |
| 49 | Kimi K3 | 0.0000 | $256.75 | 739.1M | 1.4M | 20h 0m | 1576 | 1 |
| 50 | GLM-5.3 | 0.0000 | $216.67 | 774.3M | 1.6M | 16h 7m | 1754 | 19 |