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 | 0.1123 | $1.12 | 52.3M | 255k | 18h 23m | 256 | 2 |
| 2 | DeepSeek V4 Flash Vision Exp | 0.0770 | $1.22 | 63.5M | 222k | 19h 1m | 334 | 2 |
| 3 | DeepSeek V4 Flash Vision Exp | 0.0348 | $1.44 | 75.8M | 242k | 19h 19m | 349 | 2 |
| 4 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.51 | 79.4M | 262k | 19h 14m | 406 | 2 |
| 5 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.33 | 65.8M | 275k | 19h 51m | 313 | 1 |