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 | 0.9654 | $218.42 | 430.1M | 2.0M | 15h 3m | 1010 | 21 |
| 2 | Gemini 4 Argon | 0.9568 | $288.60 | 454.6M | 2.0M | 16h 22m | 1093 | 14 |
| 3 | Gemini 4 Argon | 0.9534 | $274.81 | 581.3M | 2.0M | 17h 49m | 1368 | 15 |
| 4 | Gemini 4 Argon | 0.9529 | $147.73 | 628.9M | 2.2M | 16h 46m | 1478 | 23 |
| 5 | Gemini 4 Argon | 0.9457 | $337.69 | 476.2M | 2.1M | 17h 14m | 1055 | 18 |