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 | 0.9970 | $49.34 | 77.1M | 443k | 2h 57m | 208 | 6 |
| 2 | Claude Fable 5.1 | 0.9927 | $43.72 | 70.9M | 340k | 3h 17m | 229 | 4 |
| 3 | Claude Fable 5.1 | 0.9927 | $61.85 | 100.4M | 479k | 3h 5m | 243 | 10 |
| 4 | Claude Fable 5.1 | 0.8898 | $81.53 | 137.5M | 526k | 5h 0m | 326 | 10 |
| 5 | Grok 4.6 | 0.0610 | $858.44 | 859.7M | 2.4M | 19h 46m | 2990 | 501 |
| 6 | Kimi K3 | 0.0431 | $197.20 | 550.4M | 1.5M | 20h 1m | 1197 | 1 |
| 7 | Grok 4.6 | 0.0241 | $445.27 | 424.9M | 2.8M | 19h 59m | 1572 | 200 |
| 8 | GPT-5.6 | 0.0225 | $66.23 | 68.5M | 180k | 1h 47m | 274 | 8 |
| 9 | GPT-5.6 | 0.0225 | $81.19 | 79.4M | 199k | 1h 55m | 291 | 7 |
| 10 | GPT-5.6 | 0.0224 | $73.40 | 72.5M | 171k | 1h 41m | 273 | 8 |
| 11 | Gemini 3.7 Flash | 0.0217 | $93.80 | 813.5M | 2.3M | 19h 56m | 2141 | 1 |
| 12 | Claude Fable 5.1 | 0.0173 | $56.44 | 90.9M | 453k | 4h 18m | 228 | 8 |
| 13 | GPT-5.6 | 0.0173 | $159.04 | 153.2M | 259k | 4h 31m | 440 | 16 |
| 14 | GPT-5.6 | 0.0173 | $92.72 | 87.0M | 212k | 1h 59m | 268 | 7 |
| 15 | GLM-5.3 | 0.0173 | $171.41 | 627.5M | 1.2M | 19h 32m | 1385 | 14 |
| 16 | GLM-5.3 | 0.0173 | $236.98 | 874.4M | 1.4M | 19h 51m | 1908 | 31 |
| 17 | Grok 4.6 | 0.0117 | $262.00 | 255.9M | 1.7M | 13h 11m | 1039 | 20 |
| 18 | Kimi K3 | 0.0112 | $202.76 | 569.3M | 1.5M | 19h 50m | 1237 | 2 |
| 19 | Gemini 3.7 Flash | 0.0112 | $89.95 | 756.9M | 1.7M | 20h 0m | 1907 | 1 |
| 20 | GLM-5.3 | 0.0111 | $148.21 | 526.6M | 1.0M | 18h 49m | 1175 | 16 |
| 21 | DeepSeek V4 Flash Vision Exp | 0.0110 | $29.12 | 1761.2M | 2.9M | 19h 19m | 3911 | 24 |
| 22 | DeepSeek V4 Flash Vision Exp | 0.0053 | $22.61 | 1343.5M | 2.5M | 19h 20m | 2867 | 26 |
| 23 | GLM-5.3 | 0.0049 | $108.31 | 386.0M | 1.3M | 16h 54m | 851 | 5 |
| 24 | DeepSeek V4 Flash Vision Exp | 0.0049 | $20.65 | 1205.0M | 2.5M | 19h 56m | 2498 | 19 |
| 25 | Muse Spark 1.2 | 0.0049 | $36.55 | 207.9M | 989k | 3h 16m | 456 | 11 |
| 26 | Kimi K3 | 0.0049 | $158.40 | 411.0M | 1.7M | 20h 0m | 1010 | 1 |
| 27 | DeepSeek V4 Flash Vision Exp | 0.0049 | $17.94 | 1097.8M | 1.6M | 18h 58m | 2348 | 14 |
| 28 | Gemini 3.7 Flash | 0.0049 | $62.15 | 472.1M | 1.5M | 20h 0m | 1139 | 1 |
| 29 | DeepSeek V4 Flash Vision Exp | 0.0049 | $20.78 | 1251.0M | 2.1M | 19h 4m | 2804 | 15 |
| 30 | Kimi K3 | 0.0049 | $190.49 | 508.0M | 1.5M | 19h 54m | 1111 | 9 |
| 31 | Muse Spark 1.2 | 0.0047 | $53.94 | 336.5M | 554k | 4h 31m | 660 | 7 |
| 32 | Grok 4.6 | 0.0046 | $267.41 | 252.9M | 1.7M | 10h 33m | 927 | 132 |
| 33 | GLM-5.3 | 0.0039 | $154.89 | 566.6M | 1.0M | 19h 45m | 1350 | 18 |
| 34 | Muse Spark 1.2 | 0.0038 | $13.60 | 58.8M | 346k | 1h 50m | 189 | 3 |
| 35 | Muse Spark 1.2 | 0.0033 | $35.75 | 222.8M | 379k | 2h 39m | 489 | 7 |
| 36 | Grok 4.6 | 0.0031 | $181.59 | 175.3M | 1.4M | 8h 20m | 693 | 24 |
| 37 | Gemini 3.7 Flash | 0.0024 | $124.70 | 1220.5M | 2.9M | 20h 0m | 2795 | 1 |
| 38 | Qwen3.8-Max | 0.0013 | $12.18 | 16.0M | 1.3M | 19h 33m | 130 | 1 |
| 39 | Gemini 3.7 Flash | 0.0010 | $64.73 | 520.0M | 1.4M | 20h 0m | 1356 | 1 |
| 40 | Kimi K3 | 0.0008 | $195.88 | 529.5M | 1.7M | 20h 0m | 1266 | 2 |
| 41 | Qwen3.8-Max | 0.0001 | $13.81 | 19.3M | 1.5M | 19h 35m | 164 | 3 |
| 42 | Qwen3.8-Max | 0.0000 | $14.39 | 19.8M | 1.5M | 20h 1m | 160 | 1 |
| 43 | Inkling | 0.0000 | $14.16 | 14.7M | 37k | 1h 30m | 184 | 2 |
| 44 | Qwen3.8-Max | 0.0000 | $9.18 | 10.7M | 1.0M | 19h 50m | 100 | 1 |
| 45 | Inkling | 0.0000 | $9.30 | 9.7M | 22k | 11m | 123 | 2 |
| 46 | Inkling | 0.0000 | $12.08 | 12.6M | 23k | 14m | 161 | 2 |
| 47 | Qwen3.8-Max | 0.0000 | $13.72 | 18.7M | 1.5M | 18h 42m | 146 | 3 |
| 48 | Muse Spark 1.2 | 0.0000 | $18.50 | 97.7M | 207k | 1h 10m | 269 | 4 |
| 49 | Inkling | 0.0000 | $16.45 | 17.2M | 21k | 16m | 173 | 2 |
| 50 | Inkling | 0.0000 | $13.17 | 13.7M | 28k | 1h 27m | 186 | 2 |