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 | 0.0135 | $59.82 | 110.7M | 431k | 11h 54m | 331 | 6 |
| 2 | Muse Spark 1.2 | 0.0128 | $52.14 | 70.4M | 490k | 14h 49m | 289 | 4 |
| 3 | Muse Spark 1.2 | 0.0051 | $32.90 | 57.9M | 354k | 9h 41m | 372 | 3 |
| 4 | Muse Spark 1.2 | 0.0000† | $35.10 | 65.9M | 265k | 9h 20m | 229 | 3 |
| 5 | Muse Spark 1.2 | 0.0000† | $27.43 | 124.8M | 316k | 10h 1m | 385 | 4 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.