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 | Claude Opus 5.5 | 0.9999 | $74.48 | 265.3M | 811k | 19h 2m | 653 | 24 |
| 2 | Claude Opus 5.5 | 0.9931 | $69.52 | 233.4M | 859k | 17h 56m | 587 | 25 |
| 3 | Claude Opus 5.5 | 0.9907 | $77.01 | 274.8M | 827k | 18h 8m | 669 | 37 |
| 4 | Claude Opus 5.5 | 0.8205 | $49.70 | 176.5M | 532k | 9h 15m | 362 | 10 |
| 5 | Claude Opus 5.5 | 0.7024 | $55.16 | 202.1M | 545k | 11h 37m | 413 | 16 |