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 | 0.9286 | $102.13 | 88.3M | 440k | 7h 8m | 224 | 7 |
| 2 | Gemini 4 Argon | 0.9214 | $93.51 | 158.0M | 759k | 9h 17m | 426 | 13 |
| 3 | Gemini 4 Argon | 0.8964 | $116.54 | 131.7M | 765k | 9h 49m | 373 | 8 |
| 4 | Gemini 4 Argon | 0.8893 | $85.61 | 94.9M | 445k | 9h 1m | 199 | 6 |
| 5 | Gemini 4 Argon | 0.8679 | $74.43 | 68.7M | 419k | 7h 35m | 192 | 4 |