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 | 0.8953 | $64.06 | 109.1M | 391k | 4h 49m | 305 | 17 |
| 2 | Claude Fable 5.1 | 0.8935 | $57.22 | 97.5M | 350k | 6h 25m | 298 | 24 |
| 3 | Claude Fable 5.1 | 0.8000 | $36.76 | 59.7M | 285k | 3h 53m | 220 | 11 |
| 4 | Claude Fable 5.1 | 0.7999 | $32.01 | 51.0M | 267k | 3h 57m | 202 | 12 |
| 5 | Claude Fable 5.1 | 0.7955 | $42.10 | 68.8M | 317k | 4h 11m | 232 | 12 |
| 6 | Gemini 3.7 Flash | 0.7294 | $8.39 | 49.1M | 408k | 2h 12m | 218 | 1 |
| 7 | GLM-5.3 | 0.6985 | $72.52 | 246.9M | 707k | 19h 16m | 599 | 6 |
| 8 | Kimi K3 | 0.6250 | $60.98 | 152.4M | 478k | 16h 31m | 414 | 12 |
| 9 | Grok 4.6 | 0.5299 | $15.57 | 15.6M | 323k | 1h 52m | 106 | 4 |
| 10 | GPT-5.6 | 0.4849 | $43.38 | 52.6M | 186k | 3h 16m | 263 | 5 |
| 11 | GLM-5.3 | 0.4028 | $57.26 | 195.8M | 552k | 12h 7m | 426 | 8 |
| 12 | GLM-5.3 | 0.4017 | $72.89 | 226.5M | 514k | 17h 29m | 476 | 6 |
| 13 | Gemini 3.7 Flash | 0.4014 | $3.09 | 23.0M | 225k | 38m | 153 | 3 |
| 14 | Grok 4.6 | 0.3993 | $48.11 | 46.2M | 395k | 3h 31m | 208 | 6 |
| 15 | Kimi K3 | 0.3983 | $90.41 | 238.0M | 505k | 20h 1m | 587 | 20 |
| 16 | Kimi K3 | 0.3959 | $20.08 | 46.3M | 279k | 6h 2m | 205 | 5 |
| 17 | GLM-5.3 | 0.3930 | $77.97 | 220.3M | 559k | 15h 22m | 481 | 2 |
| 18 | Kimi K3 | 0.3804 | $70.49 | 167.8M | 452k | 19h 35m | 468 | 8 |
| 19 | Kimi K3 | 0.2995 | $53.30 | 137.6M | 418k | 11h 54m | 430 | 7 |
| 20 | GLM-5.3 | 0.2893 | $64.65 | 196.5M | 549k | 19h 1m | 419 | 8 |
| 21 | Grok 4.6 | 0.2000 | $34.68 | 34.5M | 354k | 2h 42m | 175 | 8 |
| 22 | Grok 4.6 | 0.1971 | $39.66 | 35.3M | 400k | 3h 43m | 165 | 11 |
| 23 | GPT-5.6 | 0.1823 | $39.28 | 48.9M | 195k | 2h 7m | 255 | 4 |
| 24 | Muse Spark 1.2 | 0.1013 | $11.07 | 59.7M | 393k | 2h 7m | 259 | 1 |
| 25 | Muse Spark 1.2 | 0.1000 | $12.16 | 66.0M | 402k | 2h 34m | 231 | 4 |
| 26 | Muse Spark 1.2 | 0.0563 | $26.33 | 90.8M | 427k | 5h 8m | 297 | 2 |
| 27 | Qwen3.8-Max | 0.0000 | $42.82 | 145.6M | 925k | 17h 28m | 524 | 2 |
| 28 | Inkling | 0.0000 | $4.59 | 4.7M | 24k | 22m | 105 | 2 |
| 29 | DeepSeek V4 Flash Vision Exp | 0.0000 | $4.02 | 226.3M | 587k | 18h 16m | 503 | 5 |
| 30 | Inkling | 0.0000 | $5.98 | 6.1M | 33k | 29m | 144 | 1 |
| 31 | DeepSeek V4 Flash Vision Exp | 0.0000 | $4.14 | 229.6M | 637k | 20h 0m | 483 | 1 |
| 32 | GPT-5.6 | 0.0000 | $29.74 | 37.3M | 170k | 2h 5m | 211 | 8 |
| 33 | Qwen3.8-Max | 0.0000 | $48.24 | 157.1M | 1.3M | 19h 42m | 518 | 2 |
| 34 | Gemini 3.7 Flash | 0.0000 | $5.44 | 38.0M | 299k | 1h 47m | 197 | 3 |
| 35 | Inkling | 0.0000 | $2.97 | 2.9M | 45k | 43m | 109 | 2 |
| 36 | Muse Spark 1.2 | 0.0000 | $53.10 | 223.4M | 907k | 9h 16m | 535 | 3 |
| 37 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.11 | 165.3M | 552k | 9h 15m | 409 | 6 |
| 38 | Muse Spark 1.2 | 0.0000 | $11.05 | 58.0M | 328k | 3h 11m | 241 | 2 |
| 39 | Qwen3.8-Max | 0.0000 | $42.25 | 133.5M | 1.3M | 19h 46m | 412 | 2 |
| 40 | GPT-5.6 | 0.0000 | $23.28 | 33.7M | 166k | 2h 33m | 207 | 5 |
| 41 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.44 | 189.2M | 548k | 10h 29m | 453 | 4 |
| 42 | GPT-5.6 | 0.0000 | $47.11 | 54.0M | 192k | 2h 34m | 262 | 4 |
| 43 | Inkling | 0.0000 | $6.49 | 6.6M | 47k | 1h 53m | 142 | 1 |
| 44 | Qwen3.8-Max | 0.0000 | $56.35 | 191.3M | 1.2M | 19h 55m | 589 | 1 |
| 45 | Grok 4.6 | 0.0000 | $23.09 | 23.9M | 317k | 4h 4m | 152 | 3 |
| 46 | Gemini 3.7 Flash | 0.0000 | $3.91 | 24.5M | 212k | 1h 28m | 155 | 2 |
| 47 | Gemini 3.7 Flash | 0.0000 | $3.82 | 23.6M | 220k | 46m | 162 | 2 |
| 48 | Inkling | 0.0000 | $6.06 | 6.2M | 36k | 1h 0m | 118 | 2 |
| 49 | Qwen3.8-Max | 0.0000 | $28.32 | 86.1M | 1.0M | 14h 43m | 386 | 3 |
| 50 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.67 | 205.7M | 547k | 18h 16m | 510 | 3 |