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 | 0.8206 | $37.73 | 59.2M | 320k | 3h 38m | 300 | 12 |
| 2 | Muse Spark 1.3 | 0.7474 | $18.67 | 43.3M | 220k | 4h 23m | 250 | 6 |
| 3 | Muse Spark 1.3 | 0.3726 | $625.66 | 665.8M | 679k | 19h 55m | 1128 | 223 |
| 4 | Muse Spark 1.3 | 0.3641 | $40.72 | 52.7M | 332k | 3h 49m | 257 | 8 |
| 5 | Muse Spark 1.3 | 0.0300 | $39.32 | 51.4M | 265k | 3h 54m | 261 | 8 |