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 | 0.0779 | $45.19 | 77.6M | 262k | 17h 49m | 334 | 16 |
| 2 | Claude Fable 5.1 | 0.0754 | $52.35 | 88.6M | 331k | 12h 35m | 339 | 10 |
| 3 | Claude Fable 5.1 | 0.0711 | $71.87 | 125.0M | 385k | 17h 43m | 414 | 18 |
| 4 | Claude Fable 5.1 | 0.0695 | $54.46 | 93.0M | 327k | 16h 46m | 347 | 11 |
| 5 | Claude Fable 5.1 | 0.0678 | $47.98 | 81.1M | 304k | 16h 17m | 333 | 10 |
| 6 | GPT-5.6 | 0.0416 | $183.22 | 165.9M | 262k | 15h 47m | 471 | 12 |
| 7 | GPT-5.6 | 0.0408 | $43.32 | 47.2M | 136k | 19h 34m | 249 | 10 |
| 8 | GLM-5.3 | 0.0369 | $28.71 | 91.1M | 330k | 19h 38m | 343 | 2 |
| 9 | GLM-5.3 | 0.0349 | $48.94 | 118.7M | 352k | 19h 6m | 384 | 2 |
| 10 | Kimi K3 | 0.0313 | $38.45 | 102.2M | 362k | 20h 1m | 397 | 10 |
| 11 | GLM-5.3 | 0.0298 | $35.18 | 91.1M | 311k | 19h 41m | 366 | 13 |
| 12 | DeepSeek V4 Flash Vision Exp | 0.0268 | $2.15 | 112.2M | 397k | 7h 43m | 389 | 3 |
| 13 | Kimi K3 | 0.0266 | $26.15 | 60.2M | 321k | 19h 29m | 303 | 13 |
| 14 | GLM-5.3 | 0.0264 | $29.01 | 75.1M | 335k | 17h 41m | 311 | 6 |
| 15 | Kimi K3 | 0.0251 | $50.26 | 120.4M | 460k | 19h 45m | 410 | 7 |
| 16 | Kimi K3 | 0.0250 | $34.53 | 93.2M | 354k | 19h 44m | 395 | 8 |
| 17 | GLM-5.3 | 0.0243 | $29.39 | 96.9M | 323k | 19h 43m | 356 | 1 |
| 18 | Gemini 3.7 Flash | 0.0240 | $13.44 | 120.0M | 296k | 7h 42m | 465 | 7 |
| 19 | Gemini 3.7 Flash | 0.0232 | $21.26 | 112.5M | 588k | 9h 45m | 340 | 20 |
| 20 | DeepSeek V4 Flash Vision Exp | 0.0228 | $5.13 | 304.7M | 583k | 13h 30m | 712 | 7 |
| 21 | GPT-5.6 | 0.0224 | $49.42 | 77.2M | 169k | 19h 53m | 422 | 11 |
| 22 | Grok 4.6 | 0.0221 | $127.10 | 131.5M | 617k | 19h 58m | 617 | 30 |
| 23 | Grok 4.6 | 0.0192 | $168.00 | 174.0M | 498k | 19h 58m | 768 | 68 |
| 24 | Gemini 3.7 Flash | 0.0189 | $26.85 | 83.8M | 686k | 9h 43m | 267 | 16 |
| 25 | Grok 4.6 | 0.0171 | $114.81 | 118.3M | 558k | 19h 40m | 599 | 47 |
| 26 | Qwen3.8-Max | 0.0171 | $21.55 | 69.7M | 606k | 19h 26m | 446 | 15 |
| 27 | GPT-5.6 | 0.0163 | $47.54 | 55.3M | 185k | 19h 43m | 291 | 10 |
| 28 | GPT-5.6 | 0.0159 | $41.60 | 61.4M | 164k | 18h 50m | 368 | 11 |
| 29 | Qwen3.8-Max | 0.0155 | $18.80 | 60.7M | 524k | 19h 36m | 400 | 4 |
| 30 | Muse Spark 1.2 | 0.0126 | $49.13 | 229.2M | 341k | 8h 52m | 575 | 6 |
| 31 | Grok 4.6 | 0.0126 | $162.44 | 156.4M | 577k | 19h 37m | 634 | 61 |
| 32 | Kimi K3 | 0.0120 | $62.95 | 172.7M | 576k | 20h 0m | 473 | 15 |
| 33 | Qwen3.8-Max | 0.0118 | $16.99 | 53.1M | 556k | 19h 0m | 415 | 2 |
| 34 | Gemini 3.7 Flash | 0.0110 | $6.63 | 19.2M | 229k | 5h 4m | 166 | 5 |
| 35 | Grok 4.6 | 0.0106 | $206.03 | 201.8M | 768k | 19h 59m | 845 | 63 |
| 36 | Muse Spark 1.2 | 0.0104 | $27.73 | 109.9M | 451k | 7h 13m | 358 | 10 |
| 37 | Qwen3.8-Max | 0.0098 | $20.15 | 54.4M | 994k | 19h 8m | 321 | 6 |
| 38 | Muse Spark 1.2 | 0.0097 | $69.69 | 161.5M | 457k | 8h 41m | 441 | 5 |
| 39 | Gemini 3.7 Flash | 0.0097 | $3.47 | 13.3M | 97k | 5h 22m | 153 | 4 |
| 40 | DeepSeek V4 Flash Vision Exp | 0.0094 | $6.17 | 373.9M | 627k | 11h 53m | 798 | 9 |
| 41 | Qwen3.8-Max | 0.0089 | $23.54 | 77.9M | 588k | 18h 20m | 403 | 2 |
| 42 | Muse Spark 1.2 | 0.0087 | $13.25 | 53.2M | 190k | 6h 44m | 295 | 3 |
| 43 | DeepSeek V4 Flash Vision Exp | 0.0081 | $3.17 | 180.3M | 434k | 7h 52m | 554 | 2 |
| 44 | Inkling | 0.0073 | $7.83 | 8.2M | 21k | 1h 33m | 141 | 2 |
| 45 | Muse Spark 1.2 | 0.0065 | $21.18 | 65.3M | 269k | 5h 22m | 313 | 3 |
| 46 | Inkling | 0.0061 | $5.43 | 5.5M | 41k | 1h 2m | 147 | 2 |
| 47 | Inkling | 0.0061 | $13.67 | 14.2M | 40k | 2h 24m | 225 | 2 |
| 48 | DeepSeek V4 Flash Vision Exp | 0.0056 | $3.93 | 222.7M | 553k | 14h 38m | 530 | 7 |
| 49 | Inkling | 0.0039 | $4.62 | 4.8M | 24k | 1h 6m | 101 | 1 |
| 50 | Inkling | 0.0030 | $5.70 | 5.9M | 31k | 2h 11m | 145 | 1 |