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 | 0.3095 | $25.50 | 21.9M | 121k | 19h 28m | 197 | 2 |
| 2 | Muse Spark 1.3 | 0.1429 | $16.18 | 14.5M | 230k | 20h 0m | 159 | 1 |
| 3 | Muse Spark 1.3 | 0.0000 | $22.96 | 20.6M | 169k | 19h 58m | 157 | 5 |
| 4 | Muse Spark 1.3 | 0.0000 | $12.91 | 12.2M | 103k | 19h 52m | 142 | 1 |
| 5 | Muse Spark 1.3 | 0.0000 | $30.08 | 27.4M | 216k | 19h 49m | 204 | 1 |