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 | DeepSeek V4 Flash Vision Exp | 0.1749 | $1.32 | 68.7M | 240k | 18h 36m | 359 | 6 |
| 2 | DeepSeek V4 Flash Vision Exp | 0.0826 | $1.73 | 93.5M | 273k | 12h 25m | 457 | 2 |