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 | 0.6114 | $9.23 | 47.6M | 407k | 3h 16m | 262 | 4 |
| 2 | Muse Spark 1.2 | 0.5947 | $9.36 | 45.3M | 339k | 3h 54m | 244 | 2 |
| 3 | Muse Spark 1.2 | 0.5914 | $9.21 | 41.8M | 337k | 3h 53m | 230 | 2 |
| 4 | Muse Spark 1.2 | 0.5787 | $10.64 | 52.8M | 389k | 2h 30m | 272 | 8 |
| 5 | Muse Spark 1.2 | 0.5545 | $7.70 | 42.7M | 226k | 2h 46m | 257 | 5 |