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 | 0.0235 | $5.06 | 24.8M | 145k | 2h 40m | 197 | 1 |
| 2 | Gemini 3.7 Flash | 0.0127 | $18.66 | 92.0M | 417k | 5h 34m | 318 | 2 |
| 3 | Gemini 3.7 Flash | 0.0121 | $11.51 | 63.9M | 262k | 4h 49m | 310 | 2 |
| 4 | Gemini 3.7 Flash | 0.0118 | $6.81 | 26.5M | 177k | 3h 38m | 183 | 2 |
| 5 | Gemini 3.7 Flash | 0.0041 | $7.39 | 32.0M | 185k | 3h 17m | 213 | 1 |