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 | 0.6080 | $42.76 | 36.7M | 222k | 19h 41m | 241 | 2 |
| 2 | Muse Spark 1.3 | 0.1340 | $12.49 | 16.7M | 201k | 19h 20m | 179 | 3 |
| 3 | Muse Spark 1.3 | 0.0580 | $11.26 | 13.8M | 164k | 19h 42m | 163 | 3 |
| 4 | Muse Spark 1.3 | 0.0380 | $29.75 | 31.6M | 256k | 19h 58m | 261 | 1 |
| 5 | Muse Spark 1.3 | 0.0320 | $20.03 | 29.7M | 151k | 19h 22m | 241 | 1 |