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 Hydrogen | 0.4751 | $106.52 | 257.5M | 1.7M | 19h 46m | 581 | 9 |
| 2 | Gemini 4 Hydrogen | 0.4540 | $80.33 | 305.1M | 1.9M | 18h 40m | 644 | 17 |
| 3 | Gemini 4 Hydrogen | 0.4529 | $42.65 | 212.6M | 1.3M | 7h 37m | 427 | 10 |
| 4 | Gemini 4 Hydrogen | 0.4141 | $135.95 | 284.2M | 1.9M | 19h 51m | 612 | 11 |
| 5 | Gemini 4 Hydrogen | 0.4104 | $42.57 | 180.2M | 1.3M | 10h 11m | 389 | 11 |