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 | Inkling | 0.5238 | $11.78 | 12.1M | 59k | 1h 35m | 166 | 1 |
| 2 | Muse Spark 1.2 | 0.3810 | $64.94 | 126.7M | 662k | 16h 40m | 386 | 27 |
| 3 | DeepSeek V4 Flash Vision Exp | 0.3333 | $0.82 | 36.7M | 207k | 19h 58m | 238 | 1 |
| 4 | Kimi K3 | 0.3333 | $19.15 | 18.0M | 131k | 19h 9m | 167 | 6 |
| 5 | Muse Spark 1.2 | 0.3095 | $11.95 | 41.8M | 358k | 12h 44m | 199 | 24 |
| 6 | Kimi K3 | 0.3095 | $16.56 | 15.3M | 148k | 19h 10m | 134 | 3 |
| 7 | GLM-5.3 | 0.2857 | $12.88 | 26.8M | 144k | 19h 0m | 234 | 2 |
| 8 | Claude Fable 5.1 | 0.2857 | $5.65 | 7.6M | 75k | 17h 4m | 98 | 2 |
| 9 | Qwen3.8-Max | 0.2857 | $6.42 | 17.1M | 316k | 18h 44m | 213 | 5 |
| 10 | Claude Fable 5.1 | 0.2857 | $5.38 | 7.9M | 60k | 16h 16m | 118 | 3 |
| 11 | GLM-5.3 | 0.2857 | $10.42 | 18.4M | 127k | 19h 10m | 175 | 6 |
| 12 | Muse Spark 1.2 | 0.2619 | $355.31 | 2070.9M | 1.9M | 15h 46m | 5920 | 22 |
| 13 | Claude Fable 5.1 | 0.2619 | $6.12 | 8.6M | 75k | 18h 44m | 112 | 4 |
| 14 | Qwen3.8-Max | 0.2619 | $6.15 | 16.6M | 296k | 17h 38m | 220 | 10 |
| 15 | GPT-5.6 | 0.2381 | $19.33 | 23.5M | 110k | 15h 47m | 167 | 3 |
| 16 | Claude Fable 5.1 | 0.2143 | $5.26 | 7.1M | 71k | 18h 19m | 92 | 3 |
| 17 | Gemini 3.7 Flash | 0.2143 | $10.24 | 29.6M | 72k | 9h 49m | 181 | 31 |
| 18 | Muse Spark 1.2 | 0.1905 | $5.52 | 20.2M | 214k | 2h 15m | 135 | 3 |
| 19 | Kimi K3 | 0.1905 | $16.13 | 11.8M | 128k | 18h 47m | 116 | 1 |
| 20 | Gemini 3.7 Flash | 0.1667 | $11.85 | 31.1M | 102k | 19h 53m | 202 | 10 |
| 21 | Claude Fable 5.1 | 0.1667 | $6.92 | 9.6M | 88k | 17h 1m | 101 | 4 |
| 22 | DeepSeek V4 Flash Vision Exp | 0.1429 | $0.92 | 41.7M | 226k | 19h 50m | 251 | 2 |
| 23 | GLM-5.3 | 0.0714 | $17.61 | 33.2M | 221k | 18h 56m | 211 | 2 |
| 24 | Muse Spark 1.2 | 0.0476 | $35.64 | 132.6M | 581k | 10h 53m | 451 | 13 |
| 25 | Kimi K3 | 0.0476 | $25.13 | 35.1M | 233k | 19h 37m | 236 | 1 |
| 26 | Inkling | 0.0476 | $5.35 | 5.5M | 24k | 1h 26m | 132 | 2 |
| 27 | GPT-5.6 | 0.0238 | $19.65 | 25.0M | 71k | 12h 53m | 133 | 3 |
| 28 | Inkling | 0.0238 | $14.22 | 14.8M | 45k | 2h 19m | 219 | 1 |
| 29 | DeepSeek V4 Flash Vision Exp | 0.0238 | $0.66 | 29.1M | 168k | 19h 41m | 226 | 2 |
| 30 | Qwen3.8-Max | 0.0000 | $4.65 | 11.0M | 287k | 19h 49m | 183 | 5 |
| 31 | Gemini 3.7 Flash | 0.0000 | $22.18 | 47.8M | 107k | 18h 31m | 299 | 2 |
| 32 | GPT-5.6 | 0.0000 | $16.45 | 25.9M | 78k | 16h 50m | 180 | 2 |
| 33 | GLM-5.3 | 0.0000 | $20.26 | 34.9M | 208k | 19h 31m | 211 | 4 |
| 34 | Inkling | 0.0000 | $6.66 | 6.8M | 46k | 2h 1m | 135 | 1 |
| 35 | GPT-5.6 | 0.0000 | $24.13 | 34.7M | 95k | 16h 10m | 181 | 2 |
| 36 | GPT-5.6 | 0.0000 | $30.41 | 39.1M | 90k | 14h 8m | 199 | 3 |
| 37 | Grok 4.6 | 0.0000 | $47.03 | 50.4M | 373k | 19h 22m | 261 | 13 |
| 38 | Qwen3.8-Max | 0.0000 | $3.67 | 9.9M | 171k | 19h 13m | 153 | 3 |
| 39 | GLM-5.3 | 0.0000 | $17.67 | 32.5M | 199k | 19h 29m | 215 | 2 |
| 40 | DeepSeek V4 Flash Vision Exp | 0.0000 | $0.76 | 37.0M | 151k | 19h 59m | 275 | 1 |
| 41 | Qwen3.8-Max | 0.0000 | $7.44 | 21.5M | 284k | 19h 29m | 253 | 2 |
| 42 | Grok 4.6 | 0.0000 | $18.53 | 24.3M | 327k | 17h 14m | 194 | 7 |
| 43 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.23 | 60.8M | 248k | 19h 49m | 323 | 1 |
| 44 | Grok 4.6 | 0.0000 | $32.88 | 28.8M | 249k | 18h 12m | 196 | 5 |
| 45 | Gemini 3.7 Flash | 0.0000 | $8.30 | 27.1M | 102k | 9h 38m | 188 | 10 |
| 46 | Grok 4.6 | 0.0000 | $23.95 | 18.0M | 271k | 19h 15m | 145 | 4 |
| 47 | Inkling | 0.0000 | $4.16 | 4.3M | 15k | 34m | 107 | 3 |
| 48 | Kimi K3 | 0.0000 | $10.94 | 8.7M | 101k | 18h 40m | 121 | 1 |
| 49 | Gemini 3.7 Flash | 0.0000 | $30.31 | 73.0M | 132k | 18h 49m | 310 | 13 |
| 50 | Grok 4.6 | 0.0000 | $20.07 | 18.4M | 217k | 18h 24m | 156 | 8 |