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 | 0.1827 | $179.29 | 1045.0M | 1.1M | 19h 56m | 2290 | 8 |
| 2 | Muse Spark 1.3 | 0.1338 | $375.85 | 806.9M | 1.0M | 20h 0m | 1927 | 3 |
| 3 | Muse Spark 1.3 | 0.0362 | $213.98 | 610.8M | 874k | 19h 50m | 1636 | 3 |
| 4 | Muse Spark 1.3 | 0.0269 | $429.57 | 453.8M | 790k | 19h 52m | 1245 | 2 |
| 5 | Muse Spark 1.3 | 0.0263 | $363.14 | 496.5M | 863k | 19h 59m | 1337 | 1 |