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 | Gemini 4 Argon | 0.9187 | $119.37 | 259.0M | 1.1M | 10h 5m | 645 | 1 |
| 2 | Gemini 4 Argon | 0.9106 | $303.04 | 318.6M | 1.2M | 11h 58m | 691 | 2 |
| 3 | Gemini 4 Argon | 0.9024 | $154.81 | 373.7M | 1.6M | 12h 47m | 887 | 2 |
| 4 | Gemini 4 Argon | 0.9024 | $388.42 | 369.1M | 1.6M | 13h 39m | 867 | 6 |
| 5 | Gemini 4 Argon | 0.8699 | $138.25 | 365.2M | 1.5M | 10h 38m | 856 | 2 |