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 3.7 Flash | 0.7591 | $2.33 | 9.2M | 139k | 1h 43m | 99 | 2 |
| 2 | Gemini 3.7 Flash | 0.6672 | $3.04 | 15.3M | 126k | 1h 37m | 140 | 1 |
| 3 | Gemini 3.7 Flash | 0.6446 | $3.44 | 16.9M | 214k | 2h 28m | 151 | 2 |
| 4 | Gemini 3.7 Flash | 0.6074 | $16.26 | 72.9M | 429k | 6h 43m | 280 | 5 |
| 5 | Gemini 3.7 Flash | 0.5912 | $5.63 | 44.5M | 188k | 5h 26m | 270 | 1 |