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 | 0.0247 | $73.55 | 80.1M | 351k | 10h 48m | 392 | 7 |
| 2 | Muse Spark 1.3 | 0.0215 | $70.26 | 70.8M | 222k | 11h 3m | 366 | 12 |
| 3 | Muse Spark 1.3 | 0.0200 | $64.21 | 65.3M | 198k | 19h 54m | 404 | 5 |
| 4 | Muse Spark 1.3 | 0.0192 | $39.49 | 134.3M | 306k | 19h 56m | 568 | 3 |
| 5 | Muse Spark 1.3 | 0.0124 | $64.76 | 58.2M | 224k | 18h 13m | 384 | 11 |