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 | 0.3484 | $166.03 | 303.2M | 604k | 16h 29m | 825 | 13 |
| 2 | Claude Fable 5.1 | 0.3356 | $233.87 | 425.4M | 876k | 16h 37m | 1021 | 18 |
| 3 | Claude Fable 5.1 | 0.2852 | $199.91 | 365.0M | 723k | 15h 17m | 974 | 15 |
| 4 | Claude Fable 5.1 | 0.2009 | $170.71 | 311.4M | 625k | 17h 11m | 813 | 17 |
| 5 | Gemini 3.7 Flash | 0.0802 | $35.86 | 231.6M | 242k | 6h 15m | 574 | 20 |
| 6 | Kimi K3 | 0.0603 | $148.59 | 441.7M | 786k | 16h 22m | 1028 | 15 |
| 7 | Kimi K3 | 0.0478 | $126.89 | 362.2M | 801k | 17h 53m | 936 | 9 |
| 8 | DeepSeek V4 Flash Vision Exp | 0.0237 | $8.27 | 504.6M | 723k | 9h 18m | 1260 | 11 |
| 9 | Gemini 3.7 Flash | 0.0189 | $20.57 | 157.5M | 204k | 2h 49m | 432 | 17 |
| 10 | GPT-5.6 | 0.0176 | $225.59 | 218.6M | 216k | 6h 56m | 506 | 6 |
| 11 | GLM-5.3 | 0.0162 | $93.99 | 346.3M | 474k | 11h 28m | 766 | 2 |
| 12 | Kimi K3 | 0.0132 | $145.36 | 415.9M | 1.0M | 20h 3m | 1079 | 7 |
| 13 | GLM-5.3 | 0.0129 | $109.37 | 311.0M | 484k | 17h 22m | 770 | 9 |
| 14 | Qwen3.8-Max | 0.0117 | $41.08 | 108.0M | 2.2M | 18h 38m | 484 | 6 |
| 15 | Gemini 3.7 Flash | 0.0110 | $23.00 | 164.8M | 188k | 4h 11m | 495 | 19 |
| 16 | DeepSeek V4 Flash Vision Exp | 0.0107 | $5.01 | 303.8M | 439k | 7h 50m | 723 | 8 |
| 17 | GLM-5.3 | 0.0102 | $60.68 | 223.7M | 392k | 7h 14m | 615 | 4 |
| 18 | DeepSeek V4 Flash Vision Exp | 0.0030 | $5.08 | 311.7M | 419k | 8h 3m | 781 | 6 |
| 19 | Grok 4.6 | 0.0000 | $113.60 | 103.4M | 918k | 9h 35m | 426 | 6 |
| 20 | Inkling | 0.0000 | $8.38 | 8.8M | 12k | 55m | 94 | 1 |
| 21 | GPT-5.6 | 0.0000 | $297.21 | 276.6M | 238k | 7h 17m | 549 | 5 |
| 22 | Muse Spark 1.2 | 0.0000 | $33.79 | 127.0M | 205k | 10h 23m | 356 | 5 |
| 23 | Muse Spark 1.2 | 0.0000 | $18.72 | 115.3M | 194k | 3h 23m | 350 | 4 |
| 24 | Qwen3.8-Max | 0.0000 | $34.88 | 81.5M | 2.3M | 20h 0m | 413 | 1 |
| 25 | Kimi K3 | 0.0000 | $136.80 | 389.4M | 1.1M | 20h 0m | 1006 | 19 |
| 26 | Gemini 3.7 Flash | 0.0000 | $30.61 | 210.1M | 211k | 5h 15m | 593 | 21 |
| 27 | GPT-5.6 | 0.0000 | $234.61 | 222.5M | 240k | 7h 38m | 461 | 5 |
| 28 | Grok 4.6 | 0.0000 | $240.25 | 234.7M | 1.3M | 16h 47m | 895 | 24 |
| 29 | Inkling | 0.0000 | $13.75 | 14.4M | 22k | 1h 40m | 135 | 2 |
| 30 | Kimi K3 | 0.0000 | $136.72 | 403.0M | 752k | 19h 8m | 1147 | 11 |
| 31 | Inkling | 0.0000 | $11.79 | 12.4M | 15k | 1h 2m | 121 | 1 |
| 32 | Muse Spark 1.2 | 0.0000 | $87.58 | 303.3M | 711k | 10h 13m | 562 | 5 |
| 33 | GPT-5.6 | 0.0000 | $212.19 | 205.4M | 208k | 5h 52m | 461 | 5 |
| 34 | Inkling | 0.0000 | $8.24 | 8.6M | 21k | 30m | 104 | 2 |
| 35 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.68 | 220.8M | 344k | 8h 44m | 670 | 8 |
| 36 | Inkling | 0.0000 | $13.82 | 14.5M | 21k | 59m | 137 | 2 |
| 37 | Grok 4.6 | 0.0000 | $138.74 | 131.9M | 1.2M | 8h 47m | 587 | 6 |
| 38 | Claude Fable 5.1 | 0.0000 | $232.11 | 427.5M | 765k | 16h 0m | 1023 | 35 |
| 39 | Grok 4.6 | 0.0000 | $138.58 | 127.2M | 927k | 7h 29m | 488 | 9 |
| 40 | Muse Spark 1.2 | 0.0000 | $76.77 | 223.4M | 655k | 10h 10m | 450 | 7 |
| 41 | Muse Spark 1.2 | 0.0000 | $49.18 | 242.6M | 532k | 8h 28m | 495 | 9 |
| 42 | Qwen3.8-Max | 0.0000 | $43.78 | 119.5M | 2.2M | 18h 46m | 496 | 2 |
| 43 | Qwen3.8-Max | 0.0000 | $50.74 | 159.1M | 1.7M | 16h 16m | 624 | 4 |
| 44 | GLM-5.3 | 0.0000 | $110.08 | 353.7M | 515k | 18h 43m | 761 | 18 |
| 45 | Gemini 3.7 Flash | 0.0000 | $47.46 | 341.2M | 378k | 8h 44m | 828 | 22 |
| 46 | Grok 4.6 | 0.0000 | $108.30 | 103.9M | 740k | 6h 37m | 447 | 6 |
| 47 | DeepSeek V4 Flash Vision Exp | 0.0000 | $4.87 | 296.6M | 422k | 6h 43m | 730 | 3 |
| 48 | GLM-5.3 | 0.0000 | $69.79 | 258.7M | 392k | 7h 49m | 703 | 7 |
| 49 | GPT-5.6 | 0.0000 | $355.12 | 344.3M | 254k | 10h 32m | 627 | 3 |
| 50 | Qwen3.8-Max | 0.0000 | $42.54 | 115.4M | 2.2M | 20h 0m | 491 | 1 |