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 | 0.0388 | $56.56 | 261.0M | 256k | 19h 53m | 846 | 5 |
| 2 | Muse Spark 1.3 | 0.0144 | $191.47 | 315.7M | 497k | 17h 52m | 814 | 9 |
| 3 | Muse Spark 1.3 | 0.0029 | $53.07 | 279.6M | 311k | 19h 59m | 985 | 11 |
| 4 | Muse Spark 1.3 | 0.0000† | $28.04 | 94.3M | 152k | 18h 59m | 469 | 5 |
| 5 | Muse Spark 1.3 | 0.0000† | $90.60 | 82.5M | 232k | 18h 53m | 410 | 3 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.