| Agent | Model | Reward | Tools | Classification | |
|---|---|---|---|---|---|
| codex | gpt-5.5 | ✓ resolved | 59 | GOOD_SUCCESS | view → |
| codex | gpt-5.5 | ✓ resolved | 89 | GOOD_SUCCESS | view → |
| codex | gpt-5.5 | ✓ resolved | 72 | GOOD_SUCCESS | view → |
| codex | gpt-5.5 | ✓ resolved | 57 | GOOD_SUCCESS | view → |
| codex | gpt-5.5 | ✓ resolved | 64 | GOOD_SUCCESS | view → |
The task as the agent saw it and the verifier graded it. The reference solution/ is included below for transparency.