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 | 0.6002 | $67.85 | 117.2M | 379k | 14h 26m | 401 | 17 |
| 2 | Claude Fable 5.1 | 0.5736 | $77.68 | 134.5M | 428k | 13h 49m | 450 | 16 |
| 3 | Claude Fable 5.1 | 0.5457 | $68.00 | 118.2M | 365k | 13h 15m | 419 | 21 |
| 4 | Claude Fable 5.1 | 0.5279 | $64.70 | 113.1M | 334k | 17h 24m | 419 | 17 |
| 5 | Claude Fable 5.1 | 0.4824 | $61.77 | 107.1M | 338k | 15h 49m | 418 | 16 |
| 6 | GLM-5.3 | 0.2770 | $25.86 | 86.5M | 327k | 19h 49m | 370 | 3 |
| 7 | GLM-5.3 | 0.2744 | $34.96 | 116.4M | 391k | 19h 2m | 435 | 2 |
| 8 | Kimi K3 | 0.2647 | $37.66 | 96.4M | 363k | 19h 31m | 409 | 17 |
| 9 | GPT-5.6 | 0.2623 | $123.00 | 167.4M | 279k | 11h 19m | 628 | 8 |
| 10 | GPT-5.6 | 0.2599 | $99.01 | 115.0M | 257k | 15h 3m | 528 | 10 |
| 11 | GPT-5.6 | 0.2438 | $58.48 | 76.1M | 190k | 17h 55m | 412 | 14 |
| 12 | Kimi K3 | 0.2338 | $43.76 | 111.9M | 405k | 17h 35m | 403 | 12 |
| 13 | GPT-5.6 | 0.2326 | $88.19 | 110.8M | 211k | 11h 35m | 518 | 6 |
| 14 | Grok 4.6 | 0.2286 | $85.31 | 84.1M | 498k | 7h 48m | 331 | 14 |
| 15 | Kimi K3 | 0.2242 | $36.27 | 87.9M | 412k | 11h 52m | 382 | 12 |
| 16 | Qwen3.8-Max | 0.2190 | $26.32 | 83.3M | 818k | 19h 14m | 454 | 2 |
| 17 | Qwen3.8-Max | 0.2153 | $10.82 | 27.5M | 610k | 19h 5m | 314 | 2 |
| 18 | Kimi K3 | 0.2151 | $24.45 | 60.7M | 274k | 11h 45m | 302 | 10 |
| 19 | Grok 4.6 | 0.2146 | $36.98 | 34.6M | 412k | 13h 20m | 220 | 5 |
| 20 | DeepSeek V4 Flash Vision Exp | 0.2139 | $1.97 | 101.8M | 387k | 13h 26m | 420 | 1 |
| 21 | Qwen3.8-Max | 0.2125 | $16.15 | 47.4M | 646k | 17h 46m | 362 | 2 |
| 22 | Grok 4.6 | 0.2098 | $96.38 | 88.3M | 636k | 11h 39m | 377 | 12 |
| 23 | GLM-5.3 | 0.2089 | $39.28 | 89.8M | 362k | 20h 0m | 369 | 1 |
| 24 | Grok 4.6 | 0.2060 | $71.54 | 75.2M | 388k | 6h 34m | 381 | 27 |
| 25 | GLM-5.3 | 0.2058 | $59.65 | 209.0M | 565k | 15h 11m | 548 | 8 |
| 26 | DeepSeek V4 Flash Vision Exp | 0.2028 | $2.58 | 144.1M | 374k | 19h 46m | 508 | 2 |
| 27 | Grok 4.6 | 0.2019 | $87.92 | 83.6M | 470k | 8h 37m | 361 | 10 |
| 28 | Qwen3.8-Max | 0.2005 | $15.43 | 43.7M | 693k | 18h 44m | 414 | 1 |
| 29 | Kimi K3 | 0.1961 | $13.59 | 21.1M | 194k | 9h 53m | 179 | 9 |
| 30 | DeepSeek V4 Flash Vision Exp | 0.1948 | $3.01 | 169.4M | 449k | 11h 0m | 551 | 4 |
| 31 | DeepSeek V4 Flash Vision Exp | 0.1939 | $2.93 | 164.0M | 435k | 14h 31m | 526 | 4 |
| 32 | Qwen3.8-Max | 0.1831 | $20.18 | 58.6M | 851k | 19h 8m | 443 | 2 |
| 33 | DeepSeek V4 Flash Vision Exp | 0.1818 | $2.40 | 126.7M | 415k | 10h 56m | 421 | 6 |
| 34 | Gemini 3.7 Flash | 0.1775 | $2.95 | 13.6M | 108k | 3h 17m | 129 | 2 |
| 35 | Gemini 3.7 Flash | 0.1714 | $6.92 | 27.7M | 160k | 6h 28m | 236 | 5 |
| 36 | Muse Spark 1.2 | 0.1646 | $89.68 | 227.7M | 1.2M | 20h 2m | 728 | 7 |
| 37 | GPT-5.6 | 0.1417 | $64.27 | 80.6M | 214k | 10h 2m | 389 | 3 |
| 38 | Muse Spark 1.2 | 0.1353 | $32.24 | 170.7M | 487k | 10h 37m | 551 | 5 |
| 39 | GLM-5.3 | 0.1261 | $28.93 | 86.9M | 409k | 13h 16m | 328 | 2 |
| 40 | Muse Spark 1.2 | 0.0816 | $32.40 | 192.3M | 534k | 7h 46m | 570 | 4 |
| 41 | Gemini 3.7 Flash | 0.0417 | $2.99 | 16.0M | 112k | 3h 8m | 165 | 6 |
| 42 | Gemini 3.7 Flash | 0.0412 | $3.05 | 19.8M | 150k | 3h 10m | 194 | 10 |
| 43 | Gemini 3.7 Flash | 0.0403 | $4.56 | 17.9M | 128k | 4h 20m | 145 | 8 |
| 44 | Muse Spark 1.2 | 0.0387 | $183.05 | 621.0M | 1.3M | 19h 7m | 1497 | 7 |
| 45 | Muse Spark 1.2 | 0.0356 | $37.95 | 196.7M | 1.2M | 19h 2m | 669 | 3 |
| 46 | Inkling | 0.0214 | $5.30 | 5.4M | 31k | 3h 11m | 184 | 2 |
| 47 | Inkling | 0.0209 | $6.76 | 6.9M | 44k | 2h 24m | 193 | 2 |
| 48 | Inkling | 0.0205 | $8.12 | 8.4M | 30k | 3h 20m | 185 | 1 |
| 49 | Inkling | 0.0203 | $5.44 | 5.6M | 27k | 1h 39m | 121 | 3 |
| 50 | Inkling | 0.0179 | $5.86 | 6.0M | 36k | 2h 37m | 166 | 2 |