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 | 0.4646 | $17.40 | 32.8M | 150k | 19h 29m | 250 | 11 |
| 2 | Muse Spark 1.3 | 0.4252 | $39.97 | 63.7M | 234k | 18h 47m | 401 | 10 |
| 3 | Muse Spark 1.3 | 0.4057 | $47.03 | 41.9M | 228k | 13h 41m | 311 | 11 |
| 4 | Muse Spark 1.3 | 0.3909 | $44.60 | 41.6M | 175k | 17h 28m | 283 | 7 |
| 5 | Muse Spark 1.3 | 0.3160 | $38.63 | 81.9M | 260k | 18h 49m | 434 | 13 |