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 | 0.3407 | $551.80 | 666.0M | 898k | 19h 58m | 1714 | 4 |
| 2 | Muse Spark 1.3 | 0.1099 | $305.43 | 1604.1M | 2.2M | 20h 0m | 3690 | 2 |
| 3 | Muse Spark 1.3 | 0.0549 | $522.84 | 598.7M | 1.2M | 20h 0m | 1525 | 1 |
| 4 | Muse Spark 1.3 | 0.0549 | $518.76 | 603.9M | 1.1M | 19h 59m | 1572 | 1 |
| 5 | Muse Spark 1.3 | 0.0495 | $525.95 | 562.0M | 986k | 20h 0m | 1387 | 1 |