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 | 0.9348 | $88.24 | 91.7M | 303k | 11h 17m | 409 | 2 |
| 2 | Muse Spark 1.3 | 0.9005 | $242.82 | 232.9M | 452k | 19h 26m | 628 | 1 |
| 3 | Muse Spark 1.3 | 0.4425 | $115.32 | 111.6M | 449k | 19h 59m | 385 | 1 |
| 4 | Muse Spark 1.3 | 0.4417 | $126.25 | 155.2M | 591k | 19h 59m | 465 | 1 |
| 5 | Muse Spark 1.3 | 0.4389 | $215.78 | 199.3M | 678k | 15h 8m | 502 | 24 |