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 | 0.9930 | $40.59 | 65.5M | 322k | 8h 40m | 241 | 9 |
| 2 | Claude Fable 5.1 | 0.9895 | $33.56 | 52.1M | 309k | 8h 2m | 221 | 8 |
| 3 | Qwen3.8-Max | 0.9778 | $23.74 | 79.2M | 556k | 12h 13m | 428 | 14 |
| 4 | DeepSeek V4 Flash Vision Exp | 0.9597 | $1.51 | 70.8M | 347k | 3h 23m | 283 | 4 |
| 5 | Kimi K3 | 0.9593 | $29.55 | 62.1M | 341k | 12h 49m | 285 | 15 |
| 6 | Grok 4.6 | 0.9143 | $37.23 | 34.8M | 407k | 3h 22m | 158 | 10 |
| 7 | Muse Spark 1.2 | 0.9041 | $8.87 | 38.4M | 436k | 2h 57m | 150 | 1 |
| 8 | Grok 4.6 | 0.8991 | $42.77 | 39.2M | 529k | 3h 38m | 183 | 9 |
| 9 | Grok 4.6 | 0.8827 | $39.92 | 37.7M | 462k | 3h 38m | 181 | 8 |
| 10 | Inkling | 0.8760 | $6.24 | 6.3M | 65k | 37m | 140 | 1 |
| 11 | Grok 4.6 | 0.8188 | $274.70 | 264.2M | 1.9M | 19h 38m | 1078 | 67 |
| 12 | GPT-5.6 | 0.7863 | $99.90 | 97.4M | 228k | 4h 26m | 327 | 20 |
| 13 | Qwen3.8-Max | 0.7685 | $16.66 | 51.1M | 571k | 13h 28m | 342 | 5 |
| 14 | DeepSeek V4 Flash Vision Exp | 0.7308 | $2.17 | 110.7M | 423k | 3h 32m | 374 | 9 |
| 15 | Muse Spark 1.2 | 0.7187 | $4.40 | 15.5M | 216k | 1h 29m | 110 | 2 |
| 16 | Muse Spark 1.2 | 0.7132 | $3.96 | 18.1M | 225k | 49m | 126 | 4 |
| 17 | Qwen3.8-Max | 0.4289 | $16.21 | 49.4M | 555k | 8h 58m | 285 | 8 |
| 18 | Kimi K3 | 0.4200 | $32.18 | 58.0M | 281k | 15h 50m | 280 | 8 |
| 19 | Qwen3.8-Max | 0.3449 | $15.61 | 47.3M | 543k | 7h 37m | 278 | 8 |
| 20 | Claude Fable 5.1 | 0.3345 | $30.45 | 45.8M | 311k | 4h 14m | 174 | 15 |
| 21 | Qwen3.8-Max | 0.3078 | $18.56 | 57.9M | 578k | 8h 28m | 322 | 6 |
| 22 | Grok 4.6 | 0.2104 | $116.88 | 112.5M | 824k | 9h 43m | 470 | 52 |
| 23 | GPT-5.6 | 0.2084 | $52.26 | 56.6M | 152k | 2h 42m | 244 | 5 |
| 24 | Claude Fable 5.1 | 0.2017 | $30.51 | 47.2M | 284k | 6h 48m | 194 | 9 |
| 25 | Gemini 3.7 Flash | 0.1681 | $1.72 | 9.3M | 135k | 1h 3m | 102 | 1 |
| 26 | GLM-5.3 | 0.1632 | $24.11 | 84.1M | 350k | 8h 48m | 310 | 8 |
| 27 | Muse Spark 1.2 | 0.1494 | $13.10 | 65.0M | 597k | 2h 52m | 267 | 1 |
| 28 | Gemini 3.7 Flash | 0.1295 | $1.98 | 10.2M | 141k | 50m | 105 | 3 |
| 29 | Gemini 3.7 Flash | 0.1075 | $1.62 | 9.2M | 146k | 1h 7m | 102 | 1 |
| 30 | GLM-5.3 | 0.1005 | $24.46 | 71.1M | 367k | 17h 31m | 283 | 7 |
| 31 | Kimi K3 | 0.0960 | $32.35 | 77.4M | 380k | 13h 56m | 311 | 15 |
| 32 | Gemini 3.7 Flash | 0.0798 | $2.53 | 10.3M | 161k | 1h 26m | 110 | 1 |
| 33 | Claude Fable 5.1 | 0.0778 | $29.88 | 44.4M | 316k | 2h 48m | 183 | 13 |
| 34 | GPT-5.6 | 0.0777 | $44.33 | 50.5M | 161k | 1h 56m | 229 | 6 |
| 35 | DeepSeek V4 Flash Vision Exp | 0.0718 | $2.02 | 102.8M | 397k | 15h 29m | 346 | 4 |
| 36 | DeepSeek V4 Flash Vision Exp | 0.0700 | $1.50 | 70.3M | 352k | 6h 13m | 290 | 6 |
| 37 | Gemini 3.7 Flash | 0.0647 | $3.79 | 20.7M | 194k | 1h 41m | 139 | 2 |
| 38 | Kimi K3 | 0.0626 | $34.08 | 68.6M | 372k | 14h 20m | 275 | 12 |
| 39 | DeepSeek V4 Flash Vision Exp | 0.0559 | $1.32 | 62.9M | 305k | 6h 32m | 278 | 4 |
| 40 | GLM-5.3 | 0.0517 | $9.91 | 30.6M | 263k | 2h 10m | 167 | 5 |
| 41 | Muse Spark 1.2 | 0.0498 | $2.47 | 8.0M | 164k | 1h 0m | 83 | 2 |
| 42 | GLM-5.3 | 0.0375 | $14.94 | 49.5M | 308k | 3h 28m | 223 | 2 |
| 43 | Kimi K3 | 0.0289 | $90.08 | 230.0M | 659k | 20h 0m | 555 | 1 |
| 44 | GLM-5.3 | 0.0251 | $17.68 | 60.0M | 356k | 3h 29m | 246 | 3 |
| 45 | GPT-5.6 | 0.0080 | $56.44 | 60.4M | 164k | 6h 2m | 259 | 12 |
| 46 | Inkling | 0.0078 | $3.62 | 3.6M | 51k | 2h 38m | 120 | 1 |
| 47 | GPT-5.6 | 0.0049 | $70.63 | 65.2M | 124k | 2h 29m | 194 | 6 |
| 48 | Inkling | 0.0004 | $3.37 | 3.3M | 54k | 1h 37m | 104 | 1 |
| 49 | Inkling | 0.0004 | $4.08 | 4.1M | 54k | 1h 12m | 112 | 2 |
| 50 | Inkling | 0.0000 | $2.47 | 2.5M | 36k | 1h 12m | 106 | 1 |