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 | 0.9740 | $14.41 | 21.9M | 144k | 17h 0m | 153 | 5 |
| 2 | Claude Fable 5.1 | 0.8920 | $12.71 | 19.5M | 122k | 16h 12m | 146 | 4 |
| 3 | GLM-5.3 | 0.8380 | $21.95 | 47.4M | 206k | 19h 31m | 233 | 2 |
| 4 | Claude Fable 5.1 | 0.7800 | $16.40 | 25.5M | 151k | 15h 15m | 165 | 3 |
| 5 | GLM-5.3 | 0.7220 | $12.91 | 44.6M | 176k | 19h 17m | 247 | 2 |
| 6 | Claude Fable 5.1 | 0.6180 | $15.24 | 23.4M | 145k | 17h 43m | 162 | 6 |
| 7 | Kimi K3 | 0.4620 | $12.73 | 24.9M | 159k | 19h 34m | 172 | 1 |
| 8 | Claude Fable 5.1 | 0.4080 | $13.04 | 19.3M | 141k | 15h 46m | 135 | 4 |
| 9 | GLM-5.3 | 0.3120 | $16.40 | 57.5M | 195k | 19h 21m | 314 | 2 |
| 10 | Kimi K3 | 0.3000 | $16.00 | 38.1M | 240k | 20h 0m | 187 | 1 |
| 11 | Grok 4.6 | 0.2460 | $18.57 | 19.8M | 283k | 19h 59m | 152 | 1 |
| 12 | Grok 4.6 | 0.2420 | $9.68 | 12.9M | 262k | 19h 22m | 132 | 2 |
| 13 | Qwen3.8-Max | 0.2160 | $11.97 | 38.7M | 277k | 19h 34m | 297 | 3 |
| 14 | Kimi K3 | 0.1900 | $13.63 | 32.0M | 177k | 20h 0m | 198 | 1 |
| 15 | GLM-5.3 | 0.1640 | $20.82 | 41.0M | 222k | 19h 4m | 214 | 3 |
| 16 | GLM-5.3 | 0.1580 | $16.59 | 58.5M | 233k | 19h 38m | 265 | 1 |
| 17 | Grok 4.6 | 0.1280 | $47.67 | 45.1M | 287k | 18h 35m | 259 | 5 |
| 18 | DeepSeek V4 Flash Vision Exp | 0.1100 | $1.27 | 65.0M | 240k | 20h 4m | 306 | 1 |
| 19 | Kimi K3 | 0.1040 | $11.13 | 20.9M | 147k | 19h 47m | 174 | 1 |
| 20 | Qwen3.8-Max | 0.0980 | $10.69 | 32.2M | 339k | 19h 46m | 272 | 1 |
| 21 | GPT-5.6 | 0.0900 | $19.46 | 28.7M | 100k | 17h 8m | 206 | 2 |
| 22 | Qwen3.8-Max | 0.0880 | $5.85 | 16.5M | 229k | 19h 7m | 195 | 1 |
| 23 | DeepSeek V4 Flash Vision Exp | 0.0860 | $1.47 | 79.6M | 227k | 19h 17m | 390 | 2 |
| 24 | Kimi K3 | 0.0660 | $8.10 | 17.2M | 123k | 19h 18m | 153 | 1 |
| 25 | Grok 4.6 | 0.0640 | $49.02 | 43.5M | 397k | 19h 5m | 221 | 4 |
| 26 | Gemini 3.7 Flash | 0.0620 | $5.03 | 14.3M | 76k | 5h 27m | 128 | 1 |
| 27 | GPT-5.6 | 0.0540 | $20.87 | 32.1M | 115k | 12h 56m | 241 | 3 |
| 28 | Gemini 3.7 Flash | 0.0420 | $30.72 | 72.9M | 130k | 16h 34m | 301 | 1 |
| 29 | GPT-5.6 | 0.0380 | $22.11 | 34.6M | 103k | 18h 7m | 223 | 2 |
| 30 | GPT-5.6 | 0.0360 | $61.31 | 64.5M | 145k | 15h 2m | 277 | 2 |
| 31 | Qwen3.8-Max | 0.0360 | $35.74 | 120.9M | 650k | 19h 55m | 546 | 2 |
| 32 | Grok 4.6 | 0.0340 | $48.29 | 46.2M | 363k | 16h 43m | 237 | 5 |
| 33 | Gemini 3.7 Flash | 0.0320 | $45.33 | 138.6M | 173k | 19h 58m | 396 | 1 |
| 34 | Qwen3.8-Max | 0.0300 | $11.98 | 37.6M | 292k | 18h 44m | 323 | 4 |
| 35 | Muse Spark 1.2 | 0.0300 | $18.36 | 45.0M | 166k | 4h 11m | 176 | 5 |
| 36 | Gemini 3.7 Flash | 0.0220 | $3.80 | 24.6M | 101k | 2h 41m | 142 | 2 |
| 37 | Muse Spark 1.2 | 0.0220 | $21.74 | 48.9M | 286k | 5h 11m | 239 | 11 |
| 38 | Gemini 3.7 Flash | 0.0200 | $37.07 | 96.2M | 140k | 17h 26m | 321 | 1 |
| 39 | DeepSeek V4 Flash Vision Exp | 0.0160 | $1.33 | 68.9M | 247k | 19h 56m | 345 | 2 |
| 40 | DeepSeek V4 Flash Vision Exp | 0.0160 | $1.13 | 55.9M | 221k | 19h 37m | 264 | 2 |
| 41 | GPT-5.6 | 0.0120 | $91.18 | 51.7M | 86k | 17h 41m | 228 | 4 |
| 42 | Muse Spark 1.2 | 0.0100 | $18.40 | 105.2M | 433k | 4h 43m | 251 | 5 |
| 43 | Inkling | 0.0080 | $2.60 | 2.6M | 22k | 28m | 84 | 2 |
| 44 | Muse Spark 1.2 | 0.0060 | $13.73 | 65.6M | 312k | 5h 25m | 183 | 9 |
| 45 | Inkling | 0.0000 | $8.37 | 8.7M | 31k | 38m | 169 | 2 |
| 46 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.61 | 87.5M | 249k | 20h 2m | 395 | 1 |
| 47 | Inkling | 0.0000 | $3.54 | 3.7M | 16k | 24m | 97 | 2 |
| 48 | Inkling | 0.0000 | $1.63 | 1.6M | 18k | 24m | 71 | 2 |
| 49 | Muse Spark 1.2 | 0.0000 | $196.24 | 1245.9M | 587k | 4h 6m | 2389 | 8 |
| 50 | Inkling | 0.0000 | $2.52 | 2.6M | 17k | 28m | 103 | 2 |