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 | GPT-5.6 | 0.9925 | $108.64 | 109.2M | 151k | 11h 16m | 348 | 8 |
| 2 | GPT-5.6 | 0.9918 | $109.29 | 114.5M | 152k | 15h 47m | 404 | 16 |
| 3 | GLM-5.3 | 0.9901 | $21.35 | 50.8M | 160k | 19h 5m | 353 | 1 |
| 4 | Qwen3.8-Max | 0.9731 | $4.10 | 11.4M | 180k | 17h 54m | 185 | 3 |
| 5 | GLM-5.3 | 0.9615 | $15.62 | 37.8M | 156k | 19h 29m | 294 | 2 |
| 6 | Claude Fable 5.1 | 0.9586 | $14.22 | 21.7M | 140k | 16h 34m | 179 | 11 |
| 7 | GPT-5.6 | 0.9437 | $26.20 | 41.3M | 108k | 14h 19m | 237 | 3 |
| 8 | Claude Fable 5.1 | 0.9369 | $12.11 | 18.4M | 119k | 17h 11m | 175 | 15 |
| 9 | Kimi K3 | 0.9282 | $14.81 | 21.6M | 194k | 19h 20m | 175 | 3 |
| 10 | Qwen3.8-Max | 0.9220 | $5.13 | 15.3M | 180k | 19h 14m | 209 | 2 |
| 11 | GLM-5.3 | 0.9184 | $31.31 | 62.0M | 243k | 18h 46m | 307 | 2 |
| 12 | Kimi K3 | 0.9177 | $11.72 | 20.5M | 161k | 18h 47m | 165 | 3 |
| 13 | DeepSeek V4 Flash Vision Exp | 0.9173 | $3.12 | 179.4M | 413k | 18h 25m | 558 | 6 |
| 14 | Claude Fable 5.1 | 0.9113 | $11.26 | 16.5M | 124k | 17h 50m | 150 | 5 |
| 15 | Grok 4.6 | 0.8964 | $27.94 | 18.3M | 258k | 19h 42m | 147 | 2 |
| 16 | Kimi K3 | 0.8916 | $6.54 | 9.0M | 95k | 18h 28m | 126 | 2 |
| 17 | Muse Spark 1.2 | 0.8888 | $4.08 | 20.1M | 191k | 2h 11m | 165 | 12 |
| 18 | Claude Fable 5.1 | 0.8820 | $17.05 | 26.5M | 157k | 16h 32m | 179 | 7 |
| 19 | Grok 4.6 | 0.8799 | $71.42 | 58.5M | 227k | 19h 56m | 307 | 9 |
| 20 | Muse Spark 1.2 | 0.8642 | $31.30 | 153.8M | 371k | 2h 47m | 464 | 12 |
| 21 | Gemini 3.7 Flash | 0.8422 | $11.45 | 30.2M | 159k | 8h 5m | 208 | 3 |
| 22 | Grok 4.6 | 0.8342 | $80.88 | 55.9M | 251k | 19h 37m | 265 | 10 |
| 23 | Claude Fable 5.1 | 0.8229 | $11.99 | 18.2M | 119k | 18h 9m | 171 | 13 |
| 24 | Muse Spark 1.2 | 0.8223 | $3.45 | 15.9M | 178k | 49m | 127 | 3 |
| 25 | GLM-5.3 | 0.8163 | $20.32 | 55.4M | 207k | 19h 30m | 350 | 2 |
| 26 | Qwen3.8-Max | 0.8093 | $6.94 | 20.8M | 251k | 18h 48m | 231 | 2 |
| 27 | Kimi K3 | 0.8033 | $15.11 | 21.0M | 176k | 19h 11m | 168 | 3 |
| 28 | GLM-5.3 | 0.7858 | $25.28 | 49.5M | 200k | 18h 31m | 285 | 2 |
| 29 | Muse Spark 1.2 | 0.7533 | $3.65 | 17.8M | 164k | 1h 53m | 126 | 3 |
| 30 | Kimi K3 | 0.7378 | $9.88 | 13.2M | 119k | 19h 28m | 143 | 2 |
| 31 | Gemini 3.7 Flash | 0.7285 | $10.95 | 29.5M | 154k | 8h 16m | 213 | 7 |
| 32 | Grok 4.6 | 0.7267 | $28.23 | 20.6M | 259k | 19h 44m | 159 | 3 |
| 33 | Muse Spark 1.2 | 0.7264 | $3.55 | 17.0M | 170k | 2h 17m | 144 | 3 |
| 34 | DeepSeek V4 Flash Vision Exp | 0.6906 | $1.80 | 93.9M | 332k | 18h 0m | 378 | 6 |
| 35 | Grok 4.6 | 0.5686 | $61.59 | 46.3M | 291k | 18h 29m | 250 | 4 |
| 36 | Gemini 3.7 Flash | 0.5113 | $8.21 | 27.8M | 178k | 5h 29m | 184 | 2 |
| 37 | DeepSeek V4 Flash Vision Exp | 0.4712 | $1.05 | 54.4M | 192k | 19h 29m | 342 | 2 |
| 38 | Gemini 3.7 Flash | 0.4203 | $5.25 | 21.8M | 116k | 4h 45m | 178 | 1 |
| 39 | DeepSeek V4 Flash Vision Exp | 0.2438 | $1.59 | 84.5M | 269k | 19h 1m | 389 | 5 |
| 40 | Qwen3.8-Max | 0.2071 | $6.23 | 16.9M | 295k | 18h 26m | 218 | 2 |
| 41 | Inkling | 0.0572 | $3.46 | 3.5M | 36k | 2h 37m | 136 | 1 |
| 42 | DeepSeek V4 Flash Vision Exp | 0.0562 | $2.23 | 120.5M | 374k | 18h 41m | 436 | 3 |
| 43 | Inkling | 0.0431 | $4.94 | 5.0M | 59k | 45m | 120 | 1 |
| 44 | Inkling | 0.0393 | $6.84 | 7.0M | 43k | 1h 26m | 181 | 1 |
| 45 | Inkling | 0.0179 | $5.35 | 5.4M | 56k | 1h 32m | 126 | 2 |
| 46 | Inkling | 0.0126 | $4.98 | 5.1M | 42k | 1h 33m | 148 | 2 |
| 47 | GPT-5.6 | 0.0076 | $48.99 | 56.5M | 122k | 14h 29m | 293 | 5 |
| 48 | GPT-5.6 | 0.0010 | $36.55 | 49.8M | 109k | 7h 20m | 272 | 3 |
| 49 | Qwen3.8-Max | 0.0010 | $4.41 | 12.0M | 206k | 19h 18m | 179 | 1 |
| 50 | Gemini 3.7 Flash | 0.0010 | $6.01 | 20.4M | 174k | 4h 35m | 154 | 2 |