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 | 0.4500 | $83.30 | 135.3M | 1.0M | 14h 48m | 459 | 4 |
| 2 | Muse Spark 1.3 | 0.1107 | $38.26 | 178.6M | 566k | 18h 5m | 654 | 36 |
| 3 | Muse Spark 1.3 | 0.0286 | $195.94 | 191.4M | 452k | 19h 7m | 684 | 7 |
| 4 | Muse Spark 1.3 | 0.0107 | $34.91 | 148.6M | 508k | 14h 14m | 577 | 15 |
| 5 | Muse Spark 1.3 | 0.0036 | $74.56 | 160.5M | 728k | 11h 20m | 628 | 10 |