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 1.2 | 0.0325 | $10.93 | 49.7M | 405k | 2h 44m | 182 | 3 |
| 2 | Muse Spark 1.2 | 0.0252 | $38.37 | 181.5M | 771k | 3h 21m | 481 | 13 |
| 3 | Muse Spark 1.2 | 0.0000 | $29.55 | 111.8M | 325k | 3h 53m | 331 | 2 |
| 4 | Muse Spark 1.2 | 0.0000† | $16.08 | 77.6M | 385k | 3h 9m | 254 | 2 |
| 5 | Muse Spark 1.2 | 0.0000 | $10.80 | 49.7M | 240k | 3h 10m | 226 | 3 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.