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 | 0.3487 | $65.53 | 80.8M | 133k | 10h 22m | 433 | 4 |
| 2 | GPT-5.6 | 0.3194 | $196.66 | 203.2M | 202k | 11h 49m | 678 | 23 |
| 3 | Kimi K3 | 0.3057 | $15.06 | 37.2M | 181k | 19h 11m | 275 | 4 |
| 4 | GPT-5.6 | 0.2846 | $55.29 | 72.7M | 133k | 15h 42m | 423 | 5 |
| 5 | GPT-5.6 | 0.2809 | $71.65 | 93.2M | 177k | 14h 22m | 523 | 21 |
| 6 | Grok 4.6 | 0.2557 | $99.14 | 98.0M | 624k | 19h 20m | 424 | 18 |
| 7 | GLM-5.3 | 0.2349 | $19.98 | 35.0M | 224k | 17h 41m | 192 | 3 |
| 8 | Claude Fable 5.1 | 0.2272 | $15.45 | 22.4M | 175k | 11h 13m | 164 | 5 |
| 9 | GPT-5.6 | 0.2234 | $31.29 | 52.9M | 100k | 13h 17m | 373 | 2 |
| 10 | GLM-5.3 | 0.2192 | $17.37 | 36.9M | 195k | 19h 6m | 241 | 2 |
| 11 | GLM-5.3 | 0.2082 | $16.48 | 26.8M | 198k | 19h 23m | 184 | 3 |
| 12 | Grok 4.6 | 0.1957 | $53.90 | 66.7M | 503k | 19h 24m | 395 | 24 |
| 13 | Claude Fable 5.1 | 0.1750 | $17.15 | 26.3M | 165k | 12h 46m | 182 | 6 |
| 14 | Grok 4.6 | 0.1570 | $59.53 | 57.5M | 295k | 19h 26m | 258 | 11 |
| 15 | Kimi K3 | 0.1475 | $41.51 | 100.0M | 508k | 20h 1m | 354 | 4 |
| 16 | Claude Fable 5.1 | 0.1459 | $14.90 | 22.4M | 152k | 15h 9m | 171 | 4 |
| 17 | Kimi K3 | 0.1370 | $16.05 | 38.0M | 228k | 19h 25m | 222 | 4 |
| 18 | Grok 4.6 | 0.1368 | $54.49 | 49.3M | 462k | 19h 16m | 240 | 10 |
| 19 | Claude Fable 5.1 | 0.1343 | $11.08 | 15.3M | 141k | 13h 28m | 134 | 3 |
| 20 | Gemini 3.7 Flash | 0.1194 | $22.13 | 241.0M | 134k | 10h 36m | 834 | 2 |
| 21 | DeepSeek V4 Flash Vision Exp | 0.1123 | $1.12 | 52.3M | 255k | 18h 23m | 256 | 2 |
| 22 | Kimi K3 | 0.0990 | $22.58 | 49.0M | 297k | 17h 53m | 241 | 6 |
| 23 | GLM-5.3 | 0.0984 | $17.01 | 55.5M | 261k | 19h 4m | 277 | 5 |
| 24 | GLM-5.3 | 0.0965 | $13.47 | 23.0M | 159k | 18h 59m | 180 | 2 |
| 25 | Grok 4.6 | 0.0839 | $80.45 | 75.7M | 333k | 19h 42m | 279 | 3 |
| 26 | Qwen3.8-Max | 0.0827 | $7.68 | 17.4M | 516k | 19h 49m | 226 | 3 |
| 27 | DeepSeek V4 Flash Vision Exp | 0.0770 | $1.22 | 63.5M | 222k | 19h 1m | 334 | 2 |
| 28 | Qwen3.8-Max | 0.0741 | $7.61 | 18.8M | 448k | 19h 35m | 241 | 3 |
| 29 | Qwen3.8-Max | 0.0655 | $6.87 | 15.9M | 443k | 19h 59m | 203 | 3 |
| 30 | Gemini 3.7 Flash | 0.0537 | $10.37 | 85.1M | 122k | 13h 22m | 435 | 2 |
| 31 | Gemini 3.7 Flash | 0.0405 | $25.34 | 217.9M | 182k | 10h 29m | 744 | 2 |
| 32 | DeepSeek V4 Flash Vision Exp | 0.0348 | $1.44 | 75.8M | 242k | 19h 19m | 349 | 2 |
| 33 | Claude Fable 5.1 | 0.0226 | $15.74 | 21.7M | 202k | 14h 5m | 141 | 4 |
| 34 | Qwen3.8-Max | 0.0143 | $7.32 | 18.3M | 421k | 19h 31m | 238 | 1 |
| 35 | Muse Spark 1.2 | 0.0000 | $39.25 | 85.0M | 351k | 13h 51m | 275 | 7 |
| 36 | Muse Spark 1.2 | 0.0000 | $46.70 | 116.8M | 475k | 9h 50m | 364 | 8 |
| 37 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.51 | 79.4M | 262k | 19h 14m | 406 | 2 |
| 38 | Muse Spark 1.2 | 0.0000 | $55.59 | 163.2M | 672k | 19h 37m | 567 | 1 |
| 39 | Gemini 3.7 Flash | 0.0000 | $28.88 | 259.5M | 185k | 18h 35m | 908 | 1 |
| 40 | Gemini 3.7 Flash | 0.0000 | $12.41 | 47.0M | 144k | 13h 48m | 297 | 2 |
| 41 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.33 | 65.8M | 275k | 19h 51m | 313 | 1 |
| 42 | Muse Spark 1.2 | 0.0000 | $27.04 | 48.5M | 345k | 6h 22m | 256 | 3 |
| 43 | Muse Spark 1.2 | 0.0000 | $16.21 | 19.8M | 148k | 19h 57m | 188 | 1 |
| 44 | Inkling | 0.0000 | $1.08 | 1.1M | 14k | 1h 4m | 58 | 1 |
| 45 | Kimi K3 | 0.0000 | $19.05 | 42.1M | 297k | 14h 45m | 219 | 3 |
| 46 | Inkling | 0.0000 | $1.53 | 1.5M | 16k | 1h 13m | 73 | 2 |
| 47 | Qwen3.8-Max | 0.0000 | $12.42 | 33.0M | 636k | 19h 59m | 303 | 1 |
| 48 | Inkling | 0.0000 | $3.84 | 3.9M | 25k | 5h 18m | 124 | 1 |
| 49 | Inkling | 0.0000 | $2.54 | 2.6M | 28k | 2h 1m | 88 | 1 |
| 50 | Inkling | 0.0000 | $1.63 | 1.6M | 27k | 1h 46m | 73 | 1 |