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 | 0.9394 | $221.62 | 329.8M | 1.9M | 11h 7m | 731 | 3 |
| 2 | Gemini 4 Argon | 0.9091 | $147.35 | 234.0M | 1.0M | 8h 39m | 503 | 6 |
| 3 | Gemini 4 Argon | 0.8889 | $270.20 | 399.0M | 2.4M | 13h 19m | 883 | 6 |
| 4 | Gemini 4 Argon | 0.8788 | $203.70 | 185.4M | 882k | 6h 7m | 426 | 3 |
| 5 | Gemini 4 Argon | 0.8283 | $51.57 | 147.9M | 741k | 4h 35m | 403 | 5 |