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 | 0.9976 | $451.94 | 515.6M | 941k | 16h 46m | 1261 | 2 |
| 2 | Muse Spark 1.3 | 0.4969 | $541.57 | 625.6M | 1.2M | 20h 0m | 1447 | 1 |
| 3 | Muse Spark 1.3 | 0.4002 | $540.38 | 602.2M | 792k | 20h 0m | 1400 | 1 |
| 4 | Muse Spark 1.3 | 0.0000† | $75.32 | 109.8M | 406k | 5h 42m | 461 | 6 |
| 5 | Muse Spark 1.3 | 0.0000 | $637.70 | 724.8M | 869k | 20h 0m | 1631 | 1 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.