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 | 0.1200 | $62.04 | 57.0M | 274k | 16h 49m | 329 | 3 |
| 2 | Muse Spark 1.3 | 0.1131 | $41.90 | 45.4M | 252k | 18h 50m | 304 | 7 |
| 3 | Muse Spark 1.3 | 0.1082 | $55.03 | 49.7M | 225k | 19h 54m | 361 | 1 |
| 4 | Muse Spark 1.3 | 0.1039 | $52.80 | 46.7M | 249k | 19h 50m | 351 | 6 |
| 5 | Muse Spark 1.3 | 0.0000 | $54.25 | 46.3M | 268k | 18h 59m | 310 | 2 |