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 | 0.5513 | $525.73 | 756.2M | 1.1M | 19h 57m | 1637 | 8 |
| 2 | Muse Spark 1.3 | 0.5258 | $522.21 | 631.2M | 1.1M | 19h 59m | 1757 | 5 |
| 3 | Muse Spark 1.3 | 0.5020 | $463.61 | 501.9M | 1.1M | 19h 20m | 1265 | 9 |
| 4 | Muse Spark 1.3 | 0.3680 | $506.26 | 577.2M | 925k | 19h 53m | 1567 | 1 |
| 5 | Muse Spark 1.3 | 0.0010 | $582.91 | 707.6M | 1.1M | 19h 56m | 1740 | 10 |