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 | GPT-6 Astra | 0.3006 | $2589.93 | 1231.7M | 1.9M | 19h 38m | 2587 | 122 |
| 2 | GPT-6 Astra | 0.2357 | $2732.07 | 1287.7M | 2.4M | 19h 34m | 2829 | 97 |
| 3 | GPT-6 Astra | 0.2194 | $2585.69 | 1232.6M | 2.0M | 18h 22m | 2643 | 79 |
| 4 | GPT-6 Astra | 0.1650 | $2812.60 | 1334.7M | 2.3M | 19h 56m | 2934 | 92 |