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 | GLM-5.3 Flash | 0.9637 | $1.52 | 38.6M | 196k | 15h 9m | 253 | 2 |
| 2 | GLM-5.3 Flash | 0.0000 | $1.89 | 27.2M | 201k | 18h 44m | 197 | 3 |
| 3 | GLM-5.3 Flash | 0.0000 | $1.76 | 24.4M | 187k | 19h 19m | 185 | 2 |
| 4 | GLM-5.3 Flash | 0.0000 | $2.29 | 40.6M | 258k | 17h 24m | 221 | 4 |
| 5 | GLM-5.3 Flash | 0.0000 | $1.92 | 27.6M | 178k | 19h 14m | 216 | 5 |