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 | Muse Spark 1.3 | 0.3657 | $29.63 | 28.5M | 123k | 19h 14m | 290 | 12 |
| 2 | Muse Spark 1.3 | 0.1430 | $33.98 | 30.2M | 124k | 18h 44m | 278 | 4 |
| 3 | Muse Spark 1.3 | 0.1334 | $8.50 | 30.2M | 106k | 18h 10m | 317 | 7 |
| 4 | Muse Spark 1.3 | 0.1187 | $59.14 | 56.9M | 180k | 14h 50m | 367 | 3 |
| 5 | Muse Spark 1.3 | 0.0000 | $32.86 | 29.1M | 146k | 18h 59m | 269 | 6 |