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 | 0.3604 | $65.32 | 119.8M | 246k | 14h 32m | 399 | 16 |
| 2 | Claude Fable 5.1 | 0.3524 | $77.13 | 147.0M | 311k | 14h 51m | 472 | 5 |
| 3 | Claude Fable 5.1 | 0.2715 | $77.56 | 137.7M | 370k | 10h 32m | 426 | 7 |
| 4 | Claude Fable 5.1 | 0.2491 | $104.18 | 191.5M | 350k | 15h 56m | 562 | 8 |
| 5 | Claude Fable 5.1 | 0.1812 | $69.87 | 126.5M | 304k | 15h 13m | 418 | 9 |
| 6 | GPT-5.6 | 0.1207 | $165.68 | 160.5M | 163k | 9h 38m | 416 | 7 |
| 7 | Grok 4.6 | 0.1206 | $114.81 | 93.3M | 882k | 19h 41m | 426 | 10 |
| 8 | Qwen3.8-Max | 0.1078 | $31.56 | 67.3M | 1.0M | 19h 45m | 456 | 2 |
| 9 | DeepSeek V4 Flash Vision Exp | 0.0671 | $3.79 | 218.1M | 451k | 16h 2m | 591 | 4 |
| 10 | Kimi K3 | 0.0612 | $51.38 | 138.7M | 388k | 19h 16m | 456 | 9 |
| 11 | Inkling | 0.0559 | $112.11 | 117.1M | 218k | 1h 53m | 811 | 1 |
| 12 | GLM-5.3 | 0.0490 | $52.08 | 118.9M | 330k | 18h 59m | 354 | 2 |
| 13 | DeepSeek V4 Flash Vision Exp | 0.0421 | $4.04 | 235.7M | 470k | 19h 34m | 605 | 5 |
| 14 | GLM-5.3 | 0.0406 | $79.08 | 158.6M | 318k | 18h 36m | 406 | 8 |
| 15 | Qwen3.8-Max | 0.0385 | $33.83 | 72.9M | 764k | 18h 52m | 422 | 2 |
| 16 | Kimi K3 | 0.0382 | $61.72 | 163.7M | 377k | 19h 53m | 534 | 3 |
| 17 | GLM-5.3 | 0.0363 | $101.89 | 234.7M | 397k | 19h 55m | 487 | 1 |
| 18 | Grok 4.6 | 0.0335 | $207.50 | 166.7M | 1.1M | 18h 40m | 692 | 23 |
| 19 | GLM-5.3 | 0.0278 | $99.55 | 248.0M | 367k | 18h 54m | 563 | 14 |
| 20 | Gemini 3.7 Flash | 0.0235 | $5.06 | 24.8M | 145k | 2h 40m | 197 | 1 |
| 21 | Qwen3.8-Max | 0.0216 | $32.92 | 71.7M | 721k | 19h 16m | 425 | 2 |
| 22 | Kimi K3 | 0.0211 | $44.44 | 114.5M | 382k | 20h 0m | 386 | 1 |
| 23 | Inkling | 0.0186 | $4.32 | 4.4M | 39k | 1h 1m | 122 | 1 |
| 24 | GLM-5.3 | 0.0180 | $78.52 | 153.1M | 353k | 18h 42m | 396 | 9 |
| 25 | DeepSeek V4 Flash Vision Exp | 0.0178 | $3.85 | 221.0M | 459k | 11h 59m | 555 | 7 |
| 26 | Kimi K3 | 0.0143 | $59.95 | 154.4M | 389k | 20h 1m | 507 | 2 |
| 27 | Muse Spark 1.2 | 0.0135 | $59.82 | 110.7M | 431k | 11h 54m | 331 | 6 |
| 28 | Inkling | 0.0129 | $1.44 | 1.4M | 20k | 2h 0m | 84 | 1 |
| 29 | Muse Spark 1.2 | 0.0128 | $52.14 | 70.4M | 490k | 14h 49m | 289 | 4 |
| 30 | Gemini 3.7 Flash | 0.0127 | $18.66 | 92.0M | 417k | 5h 34m | 318 | 2 |
| 31 | Grok 4.6 | 0.0122 | $159.04 | 128.5M | 975k | 18h 46m | 569 | 20 |
| 32 | Gemini 3.7 Flash | 0.0121 | $11.51 | 63.9M | 262k | 4h 49m | 310 | 2 |
| 33 | Gemini 3.7 Flash | 0.0118 | $6.81 | 26.5M | 177k | 3h 38m | 183 | 2 |
| 34 | DeepSeek V4 Flash Vision Exp | 0.0114 | $4.73 | 279.3M | 524k | 19h 31m | 681 | 4 |
| 35 | Qwen3.8-Max | 0.0061 | $53.75 | 151.0M | 965k | 20h 0m | 695 | 2 |
| 36 | Muse Spark 1.2 | 0.0051 | $32.90 | 57.9M | 354k | 9h 41m | 372 | 3 |
| 37 | Grok 4.6 | 0.0043 | $218.28 | 183.9M | 1.3M | 14h 37m | 752 | 15 |
| 38 | Gemini 3.7 Flash | 0.0041 | $7.39 | 32.0M | 185k | 3h 17m | 213 | 1 |
| 39 | Inkling | 0.0031 | $5.44 | 5.4M | 67k | 1h 58m | 120 | 2 |
| 40 | Inkling | 0.0025 | $2.42 | 2.4M | 30k | 2h 1m | 89 | 2 |
| 41 | DeepSeek V4 Flash Vision Exp | 0.0000† | $2.30 | 127.9M | 331k | 19h 43m | 454 | 3 |
| 42 | GPT-5.6 | 0.0000† | $58.14 | 63.0M | 111k | 13h 6m | 288 | 4 |
| 43 | GPT-5.6 | 0.0000† | $25.75 | 38.4M | 104k | 16h 16m | 218 | 4 |
| 44 | Grok 4.6 | 0.0000† | $57.50 | 52.5M | 468k | 7h 59m | 252 | 3 |
| 45 | Qwen3.8-Max | 0.0000† | $18.02 | 51.8M | 431k | 20h 1m | 433 | 2 |
| 46 | GPT-5.6 | 0.0000† | $51.99 | 57.9M | 124k | 4h 17m | 277 | 6 |
| 47 | GPT-5.6 | 0.0000† | $79.43 | 80.8M | 113k | 10h 50m | 285 | 4 |
| 48 | Kimi K3 | 0.0000† | $56.92 | 159.4M | 376k | 20h 0m | 521 | 1 |
| 49 | Muse Spark 1.2 | 0.0000† | $35.10 | 65.9M | 265k | 9h 20m | 229 | 3 |
| 50 | Muse Spark 1.2 | 0.0000† | $27.43 | 124.8M | 316k | 10h 1m | 385 | 4 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.