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 | 0.9331 | $62.26 | 106.8M | 367k | 8h 14m | 284 | 8 |
| 2 | Claude Fable 5.1 | 0.9314 | $52.87 | 90.3M | 319k | 5h 49m | 274 | 9 |
| 3 | Kimi K3 | 0.9307 | $34.42 | 90.2M | 306k | 9h 26m | 306 | 5 |
| 4 | GPT-5.6 | 0.9241 | $103.11 | 107.4M | 168k | 5h 28m | 369 | 8 |
| 5 | Claude Fable 5.1 | 0.9205 | $68.80 | 118.8M | 390k | 9h 16m | 323 | 6 |
| 6 | Kimi K3 | 0.9196 | $29.20 | 75.3M | 345k | 8h 0m | 286 | 8 |
| 7 | Claude Fable 5.1 | 0.9192 | $42.87 | 72.2M | 281k | 5h 13m | 226 | 5 |
| 8 | Claude Fable 5.1 | 0.9186 | $55.53 | 95.2M | 329k | 8h 32m | 279 | 10 |
| 9 | GLM-5.3 | 0.9144 | $51.16 | 175.7M | 465k | 14h 14m | 461 | 2 |
| 10 | GLM-5.3 | 0.9094 | $42.10 | 140.4M | 401k | 16h 39m | 404 | 2 |
| 11 | Kimi K3 | 0.9090 | $15.06 | 37.9M | 188k | 7h 2m | 204 | 7 |
| 12 | GLM-5.3 | 0.9087 | $43.47 | 155.3M | 374k | 16h 47m | 478 | 2 |
| 13 | GPT-5.6 | 0.9087 | $34.04 | 44.6M | 108k | 4h 5m | 199 | 9 |
| 14 | Grok 4.6 | 0.9085 | $149.23 | 138.7M | 1.3M | 12h 2m | 586 | 2 |
| 15 | GPT-5.6 | 0.9062 | $69.52 | 78.1M | 124k | 3h 50m | 295 | 3 |
| 16 | Grok 4.6 | 0.9047 | $29.23 | 30.9M | 270k | 3h 12m | 158 | 1 |
| 17 | GPT-5.6 | 0.9014 | $57.11 | 66.4M | 129k | 4h 8m | 267 | 5 |
| 18 | Grok 4.6 | 0.9010 | $76.51 | 66.4M | 639k | 9h 42m | 273 | 2 |
| 19 | Kimi K3 | 0.8899 | $31.51 | 84.6M | 291k | 12h 22m | 348 | 3 |
| 20 | GPT-5.6 | 0.8681 | $66.06 | 72.8M | 105k | 4h 8m | 267 | 4 |
| 21 | Qwen3.8-Max | 0.4407 | $34.51 | 98.7M | 1.3M | 19h 41m | 423 | 2 |
| 22 | Qwen3.8-Max | 0.4404 | $41.19 | 95.2M | 1.6M | 20h 1m | 427 | 1 |
| 23 | DeepSeek V4 Flash Vision Exp | 0.4396 | $4.92 | 297.3M | 464k | 19h 11m | 681 | 11 |
| 24 | DeepSeek V4 Flash Vision Exp | 0.4384 | $3.53 | 204.1M | 419k | 17h 55m | 562 | 3 |
| 25 | DeepSeek V4 Flash Vision Exp | 0.3550 | $2.99 | 168.7M | 386k | 19h 32m | 453 | 3 |
| 26 | Qwen3.8-Max | 0.2981 | $45.25 | 145.8M | 997k | 19h 53m | 526 | 1 |
| 27 | Kimi K3 | 0.2838 | $85.29 | 208.6M | 954k | 19h 56m | 558 | 3 |
| 28 | DeepSeek V4 Flash Vision Exp | 0.2720 | $3.61 | 208.7M | 436k | 14h 28m | 562 | 11 |
| 29 | Grok 4.6 | 0.2716 | $127.41 | 108.5M | 1.7M | 19h 30m | 464 | 4 |
| 30 | DeepSeek V4 Flash Vision Exp | 0.2506 | $3.27 | 186.8M | 413k | 17h 5m | 493 | 5 |
| 31 | Grok 4.6 | 0.2296 | $214.90 | 198.0M | 1.7M | 19h 41m | 759 | 13 |
| 32 | GLM-5.3 | 0.0945 | $60.08 | 134.7M | 351k | 20h 1m | 432 | 1 |
| 33 | Qwen3.8-Max | 0.0664 | $30.34 | 85.4M | 1.2M | 19h 11m | 360 | 2 |
| 34 | Inkling | 0.0429 | $17.12 | 17.9M | 30k | 2h 11m | 192 | 1 |
| 35 | Inkling | 0.0404 | $13.85 | 14.5M | 23k | 1h 11m | 142 | 1 |
| 36 | Gemini 3.7 Flash | 0.0349 | $23.63 | 178.6M | 776k | 6h 26m | 569 | 1 |
| 37 | Gemini 3.7 Flash | 0.0347 | $27.48 | 166.6M | 453k | 6h 47m | 438 | 1 |
| 38 | Gemini 3.7 Flash | 0.0331 | $42.63 | 248.9M | 797k | 11h 49m | 716 | 1 |
| 39 | Muse Spark 1.2 | 0.0325 | $10.93 | 49.7M | 405k | 2h 44m | 182 | 3 |
| 40 | Gemini 3.7 Flash | 0.0317 | $28.92 | 149.4M | 462k | 8h 34m | 380 | 1 |
| 41 | Gemini 3.7 Flash | 0.0310 | $36.97 | 183.1M | 560k | 8h 49m | 483 | 1 |
| 42 | Inkling | 0.0305 | $12.93 | 13.5M | 35k | 14m | 141 | 1 |
| 43 | Muse Spark 1.2 | 0.0252 | $38.37 | 181.5M | 771k | 3h 21m | 481 | 13 |
| 44 | GLM-5.3 | 0.0239 | $77.39 | 173.5M | 511k | 19h 46m | 464 | 11 |
| 45 | Qwen3.8-Max | 0.0000 | $50.91 | 123.3M | 1.9M | 19h 56m | 467 | 1 |
| 46 | Muse Spark 1.2 | 0.0000 | $29.55 | 111.8M | 325k | 3h 53m | 331 | 2 |
| 47 | Muse Spark 1.2 | 0.0000† | $16.08 | 77.6M | 385k | 3h 9m | 254 | 2 |
| 48 | Inkling | 0.0000 | $16.05 | 16.8M | 29k | 1h 23m | 176 | 2 |
| 49 | Muse Spark 1.2 | 0.0000 | $10.80 | 49.7M | 240k | 3h 10m | 226 | 3 |
| 50 | Inkling | 0.0000 | $11.47 | 11.9M | 30k | 1h 18m | 145 | 2 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.