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 | 0.9429 | $45.45 | 65.6M | 338k | 12h 24m | 221 | 3 |
| 2 | Claude Opus 5 | 0.8750 | $46.27 | 65.7M | 362k | 13h 32m | 222 | 5 |
| 3 | Claude Opus 5 | 0.8500 | $61.18 | 94.0M | 386k | 14h 7m | 294 | 4 |
| 4 | Claude Opus 5 | 0.8429 | $60.29 | 91.4M | 395k | 14h 7m | 252 | 7 |
| 5 | Claude Opus 5 | 0.7643 | $37.81 | 52.1M | 323k | 13h 43m | 213 | 4 |