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 | 0.9536 | $56.70 | 98.3M | 311k | 9h 23m | 314 | 7 |
| 2 | Claude Fable 5.1 | 0.9536 | $46.08 | 78.9M | 273k | 10h 59m | 276 | 9 |
| 3 | Claude Fable 5.1 | 0.9429 | $31.38 | 51.1M | 239k | 11h 53m | 233 | 6 |
| 4 | GPT-5.6 | 0.8893 | $28.42 | 45.1M | 149k | 6h 33m | 291 | 7 |
| 5 | GPT-5.6 | 0.8607 | $35.99 | 57.3M | 138k | 6h 13m | 336 | 13 |
| 6 | Claude Fable 5.1 | 0.8357 | $41.84 | 71.9M | 245k | 9h 32m | 252 | 11 |
| 7 | GPT-5.6 | 0.8071 | $20.62 | 32.5M | 99k | 10h 50m | 196 | 10 |
| 8 | GPT-5.6 | 0.8000 | $20.53 | 30.5M | 123k | 2h 52m | 197 | 3 |
| 9 | Claude Fable 5.1 | 0.7929 | $38.22 | 64.0M | 257k | 7h 37m | 245 | 4 |
| 10 | Kimi K3 | 0.7571 | $29.23 | 77.1M | 277k | 14h 20m | 314 | 2 |
| 11 | GPT-5.6 | 0.7357 | $15.51 | 21.1M | 106k | 11h 38m | 168 | 9 |
| 12 | Grok 4.6 | 0.6036 | $87.29 | 70.2M | 604k | 8h 33m | 259 | 9 |
| 13 | Grok 4.6 | 0.5857 | $104.51 | 99.3M | 819k | 14h 17m | 453 | 24 |
| 14 | GLM-5.3 | 0.5357 | $48.03 | 138.0M | 410k | 14h 33m | 388 | 9 |
| 15 | Kimi K3 | 0.5071 | $31.51 | 82.4M | 325k | 14h 46m | 311 | 4 |
| 16 | Kimi K3 | 0.4286 | $27.43 | 64.3M | 286k | 14h 50m | 256 | 11 |
| 17 | Gemini 3.7 Flash | 0.4250 | $12.09 | 51.0M | 293k | 4h 11m | 266 | 3 |
| 18 | GLM-5.3 | 0.4214 | $29.52 | 79.9M | 302k | 14h 26m | 305 | 6 |
| 19 | Grok 4.6 | 0.4071 | $107.37 | 99.7M | 852k | 13h 36m | 443 | 17 |
| 20 | Muse Spark 1.2 | 0.4036 | $5.41 | 24.7M | 331k | 4h 44m | 150 | 2 |
| 21 | Muse Spark 1.2 | 0.4036 | $6.73 | 30.6M | 391k | 4h 23m | 132 | 4 |
| 22 | Muse Spark 1.2 | 0.3750 | $11.18 | 57.5M | 431k | 6h 54m | 254 | 6 |
| 23 | GLM-5.3 | 0.3607 | $36.05 | 73.5M | 339k | 13h 30m | 259 | 4 |
| 24 | Muse Spark 1.2 | 0.3429 | $9.01 | 40.4M | 451k | 7h 47m | 197 | 4 |
| 25 | Kimi K3 | 0.3143 | $28.91 | 69.9M | 341k | 12h 50m | 253 | 2 |
| 26 | Gemini 3.7 Flash | 0.3000 | $23.11 | 214.3M | 578k | 5h 22m | 524 | 1 |
| 27 | GLM-5.3 | 0.2893 | $25.26 | 83.8M | 284k | 14h 38m | 339 | 4 |
| 28 | Grok 4.6 | 0.2786 | $78.34 | 65.1M | 979k | 10h 29m | 301 | 8 |
| 29 | GLM-5.3 | 0.2571 | $27.02 | 69.8M | 315k | 14h 43m | 253 | 6 |
| 30 | Gemini 3.7 Flash | 0.2393 | $20.54 | 111.4M | 562k | 4h 43m | 327 | 1 |
| 31 | Muse Spark 1.2 | 0.2071 | $9.69 | 39.5M | 748k | 4h 22m | 138 | 7 |
| 32 | Inkling | 0.2000 | $1.23 | 1.2M | 15k | 1h 37m | 46 | 1 |
| 33 | DeepSeek V4 Flash Vision Exp | 0.1786 | $2.02 | 107.0M | 337k | 14h 34m | 328 | 2 |
| 34 | Kimi K3 | 0.1429 | $43.61 | 116.1M | 397k | 14h 40m | 395 | 2 |
| 35 | Qwen3.8-Max | 0.1357 | $20.20 | 59.6M | 794k | 13h 51m | 345 | 3 |
| 36 | DeepSeek V4 Flash Vision Exp | 0.1214 | $2.99 | 164.7M | 448k | 8h 44m | 423 | 5 |
| 37 | Grok 4.6 | 0.0929 | $172.71 | 159.1M | 1.1M | 14h 32m | 609 | 14 |
| 38 | Inkling | 0.0786 | $1.37 | 1.4M | 14k | 43m | 62 | 1 |
| 39 | Qwen3.8-Max | 0.0750 | $16.70 | 49.8M | 638k | 13h 27m | 335 | 3 |
| 40 | Qwen3.8-Max | 0.0536 | $12.92 | 35.1M | 623k | 13h 47m | 238 | 3 |
| 41 | Gemini 3.7 Flash | 0.0536 | $30.51 | 186.7M | 1.3M | 5h 45m | 513 | 2 |
| 42 | Qwen3.8-Max | 0.0536 | $22.79 | 70.5M | 780k | 13h 7m | 415 | 3 |
| 43 | Gemini 3.7 Flash | 0.0429 | $30.88 | 192.0M | 568k | 8h 45m | 506 | 2 |
| 44 | Inkling | 0.0393 | $5.27 | 5.4M | 45k | 1h 49m | 127 | 2 |
| 45 | DeepSeek V4 Flash Vision Exp | 0.0357 | $2.71 | 145.6M | 448k | 14h 17m | 377 | 7 |
| 46 | DeepSeek V4 Flash Vision Exp | 0.0143 | $2.49 | 130.6M | 440k | 11h 4m | 400 | 10 |
| 47 | Inkling | 0.0143 | $2.10 | 2.1M | 21k | 28m | 83 | 1 |
| 48 | Qwen3.8-Max | 0.0071 | $26.05 | 82.8M | 805k | 13h 22m | 436 | 3 |
| 49 | DeepSeek V4 Flash Vision Exp | 0.0036 | $2.74 | 145.9M | 463k | 9h 28m | 372 | 6 |
| 50 | Inkling | 0.0000 | $3.91 | 4.0M | 36k | 2h 12m | 98 | 2 |