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 | 0.2729 | $60.32 | 65.3M | 317k | 6h 41m | 357 | 11 |
| 2 | Muse Spark 1.3 | 0.2285 | $27.01 | 79.4M | 314k | 19h 7m | 407 | 8 |
| 3 | Muse Spark 1.3 | 0.2112 | $78.14 | 76.4M | 260k | 11h 8m | 358 | 3 |
| 4 | Muse Spark 1.3 | 0.1309 | $65.04 | 67.7M | 249k | 11h 11m | 371 | 6 |
| 5 | Muse Spark 1.3 | 0.1170 | $63.50 | 77.9M | 313k | 5h 49m | 326 | 3 |