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 | 0.9104 | $105.47 | 115.9M | 895k | 5h 40m | 315 | 6 |
| 2 | Gemini 4 Argon | 0.9046 | $83.33 | 130.1M | 792k | 5h 37m | 359 | 3 |
| 3 | Gemini 4 Argon | 0.8993 | $145.24 | 118.2M | 769k | 6h 54m | 331 | 8 |
| 4 | Gemini 4 Argon | 0.8884 | $91.03 | 70.1M | 500k | 3h 12m | 195 | 3 |
| 5 | Gemini 4 Argon | 0.8832 | $36.18 | 98.9M | 556k | 3h 28m | 236 | 3 |