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 | 0.9448 | $95.08 | 678.0M | 1.4M | 19h 49m | 1660 | 1 |
| 2 | Gemini 3.7 Flash | 0.9361 | $54.83 | 453.2M | 1.3M | 12h 43m | 1224 | 1 |
| 3 | Gemini 3.7 Flash | 0.1248 | $74.81 | 557.5M | 1.1M | 14h 22m | 1217 | 1 |
| 4 | Gemini 3.7 Flash | 0.0087 | $48.94 | 384.1M | 939k | 13h 20m | 1118 | 1 |
| 5 | Gemini 3.7 Flash | 0.0000 | $101.50 | 861.0M | 1.8M | 19h 58m | 2092 | 1 |