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 | 0.9334 | $206.78 | 382.0M | 1.3M | 15h 47m | 877 | 5 |
| 2 | Gemini 4 Argon | 0.9080 | $207.90 | 379.4M | 1.5M | 15h 34m | 854 | 10 |
| 3 | Gemini 4 Argon | 0.8458 | $261.90 | 442.3M | 1.8M | 19h 2m | 1056 | 6 |
| 4 | Gemini 4 Argon | 0.7148 | $130.35 | 185.9M | 816k | 8h 32m | 449 | 3 |
| 5 | Gemini 4 Argon | 0.7072 | $170.81 | 258.5M | 1.2M | 8h 45m | 673 | 3 |