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 | 0.0231 | $411.74 | 433.6M | 529k | 18h 32m | 875 | 4 |
| 2 | Muse Spark 1.3 | 0.0192 | $411.77 | 452.6M | 517k | 18h 56m | 944 | 8 |
| 3 | Muse Spark 1.3 | 0.0168 | $495.72 | 581.2M | 737k | 19h 59m | 1530 | 3 |
| 4 | Muse Spark 1.3 | 0.0000 | $472.59 | 577.9M | 275k | 18h 58m | 1276 | 12 |
| 5 | Muse Spark 1.3 | 0.0000 | $394.96 | 454.8M | 322k | 15h 45m | 1021 | 12 |