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 | 0.8586 | $166.41 | 276.3M | 1.2M | 9h 57m | 632 | 17 |
| 2 | Claude Fable 5.1 | 0.7677 | $93.05 | 145.4M | 837k | 3h 54m | 417 | 4 |
| 3 | Claude Fable 5.1 | 0.7071 | $96.79 | 153.4M | 827k | 4h 2m | 413 | 8 |
| 4 | Claude Fable 5.1 | 0.6970 | $69.08 | 107.8M | 623k | 2h 37m | 227 | 2 |
| 5 | Claude Fable 5.1 | 0.6667 | $96.05 | 148.5M | 898k | 4h 16m | 406 | 6 |
| 6 | Gemini 3.7 Flash | 0.6263 | $99.31 | 1037.7M | 2.0M | 6h 16m | 2577 | 4 |
| 7 | Grok 4.6 | 0.5657 | $717.25 | 714.4M | 2.7M | 18h 22m | 2483 | 266 |
| 8 | GLM-5.3 | 0.5354 | $171.96 | 618.6M | 1.7M | 18h 15m | 1441 | 4 |
| 9 | Gemini 3.7 Flash | 0.5253 | $121.42 | 1230.5M | 2.0M | 12h 5m | 2949 | 3 |
| 10 | Grok 4.6 | 0.5253 | $835.65 | 836.5M | 3.1M | 20h 0m | 3128 | 205 |
| 11 | GLM-5.3 | 0.4949 | $235.96 | 867.9M | 1.6M | 17h 11m | 1905 | 18 |
| 12 | Grok 4.6 | 0.4848 | $586.10 | 582.0M | 3.0M | 17h 34m | 2322 | 89 |
| 13 | Gemini 3.7 Flash | 0.4747 | $76.85 | 790.2M | 1.6M | 4h 46m | 2017 | 2 |
| 14 | Grok 4.6 | 0.4646 | $1191.20 | 1187.2M | 2.5M | 19h 58m | 3879 | 96 |
| 15 | Grok 4.6 | 0.4545 | $165.93 | 154.1M | 860k | 5h 37m | 563 | 37 |
| 16 | Gemini 3.7 Flash | 0.4444 | $80.51 | 766.1M | 1.3M | 6h 23m | 1793 | 7 |
| 17 | GPT-5.6 | 0.4444 | $366.07 | 350.2M | 455k | 6h 25m | 797 | 22 |
| 18 | GLM-5.3 | 0.4444 | $158.88 | 578.0M | 1.3M | 10h 53m | 1155 | 4 |
| 19 | GLM-5.3 | 0.4141 | $190.24 | 693.2M | 1.5M | 19h 41m | 1705 | 30 |
| 20 | GPT-5.6 | 0.4141 | $307.32 | 296.1M | 386k | 4h 30m | 783 | 15 |
| 21 | GPT-5.6 | 0.3939 | $538.95 | 528.2M | 617k | 6h 30m | 1280 | 21 |
| 22 | Gemini 3.7 Flash | 0.3737 | $126.28 | 1246.3M | 2.0M | 12h 6m | 2921 | 2 |
| 23 | Qwen3.8-Max | 0.3737 | $145.98 | 524.1M | 2.1M | 19h 26m | 1338 | 1 |
| 24 | Qwen3.8-Max | 0.3434 | $127.04 | 463.9M | 1.6M | 19h 13m | 987 | 4 |
| 25 | GPT-5.6 | 0.3333 | $187.27 | 186.7M | 262k | 2h 15m | 515 | 8 |
| 26 | GLM-5.3 | 0.3131 | $152.26 | 545.3M | 1.3M | 16h 57m | 1164 | 23 |
| 27 | Qwen3.8-Max | 0.3030 | $96.60 | 342.7M | 1.6M | 18h 43m | 760 | 2 |
| 28 | Qwen3.8-Max | 0.3030 | $110.14 | 386.5M | 2.0M | 19h 56m | 947 | 1 |
| 29 | Qwen3.8-Max | 0.2727 | $126.58 | 455.7M | 1.9M | 19h 26m | 951 | 7 |
| 30 | GPT-5.6 | 0.2626 | $226.84 | 221.2M | 327k | 3h 7m | 592 | 13 |
| 31 | Muse Spark 1.2 | 0.1313 | $32.05 | 183.6M | 731k | 2h 8m | 465 | 1 |
| 32 | Muse Spark 1.2 | 0.0707 | $10.81 | 53.3M | 351k | 1h 35m | 223 | 2 |
| 33 | Muse Spark 1.2 | 0.0707 | $32.82 | 175.7M | 815k | 3h 21m | 461 | 1 |
| 34 | Muse Spark 1.2 | 0.0505 | $8.77 | 48.8M | 242k | 1h 16m | 196 | 2 |
| 35 | Muse Spark 1.2 | 0.0404 | $5.34 | 27.9M | 188k | 26m | 143 | 2 |
| 36 | DeepSeek V4 Flash Vision Exp | 0.0000 | $11.65 | 704.6M | 1.2M | 10h 40m | 1549 | 15 |
| 37 | Kimi K3 | 0.0000 | $179.57 | 474.0M | 1.9M | 19h 42m | 1215 | 9 |
| 38 | Kimi K3 | 0.0000 | $215.15 | 588.2M | 1.9M | 19h 56m | 1405 | 3 |
| 39 | DeepSeek V4 Flash Vision Exp | 0.0000 | $19.65 | 1192.1M | 2.0M | 18h 3m | 2398 | 10 |
| 40 | Kimi K3 | 0.0000 | $199.08 | 565.4M | 1.4M | 19h 58m | 1271 | 1 |
| 41 | Kimi K3 | 0.0000 | $204.94 | 570.3M | 1.7M | 19h 34m | 1399 | 3 |
| 42 | Kimi K3 | 0.0000 | $193.03 | 529.1M | 1.8M | 19h 58m | 1263 | 1 |
| 43 | DeepSeek V4 Flash Vision Exp | 0.0000 | $20.48 | 1199.6M | 2.4M | 11h 32m | 2563 | 9 |
| 44 | Inkling | 0.0000 | $4.42 | 4.6M | 23k | 45m | 83 | 1 |
| 45 | DeepSeek V4 Flash Vision Exp | 0.0000 | $21.51 | 1287.0M | 2.2M | 19h 10m | 2904 | 13 |
| 46 | Inkling | 0.0000 | $19.30 | 20.1M | 40k | 1h 20m | 170 | 2 |
| 47 | Inkling | 0.0000 | $1.04 | 1.1M | 10k | 27m | 52 | 2 |
| 48 | DeepSeek V4 Flash Vision Exp | 0.0000 | $19.68 | 1182.5M | 2.0M | 19h 8m | 2617 | 23 |
| 49 | Inkling | 0.0000 | $5.07 | 5.3M | 18k | 1h 13m | 110 | 2 |
| 50 | Inkling | 0.0000 | $5.21 | 5.3M | 32k | 15m | 124 | 2 |