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 | 0.3829 | $88.55 | 356.6M | 541k | 7h 12m | 754 | 3 |
| 2 | Muse Spark 1.2 | 0.3711 | $10.87 | 42.0M | 256k | 3h 30m | 227 | 4 |
| 3 | Muse Spark 1.2 | 0.3611 | $12.50 | 32.3M | 167k | 4h 4m | 213 | 5 |
| 4 | Muse Spark 1.2 | 0.3544 | $13.53 | 50.0M | 335k | 4h 26m | 248 | 4 |
| 5 | Muse Spark 1.2 | 0.3434 | $13.40 | 47.8M | 217k | 5h 21m | 241 | 5 |