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 | 0.0000 | $15.42 | 90.0M | 327k | 41m | 286 | 2 |
| 2 | Muse Spark 1.2 | 0.0000 | $16.97 | 85.6M | 384k | 1h 38m | 227 | 4 |
| 3 | Muse Spark 1.2 | 0.0000 | $11.90 | 64.7M | 340k | 1h 14m | 223 | 2 |
| 4 | Muse Spark 1.2 | 0.0000 | $35.70 | 203.8M | 978k | 3h 29m | 468 | 8 |
| 5 | Muse Spark 1.2 | 0.0000 | $27.98 | 159.1M | 568k | 1h 40m | 345 | 2 |