| Agent | Model | Reward | Runtime | Tools | Classification | |
|---|---|---|---|---|---|---|
| claude-code | claude-opus-4-8 | ✗ failed | — | 11 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 13 | BAD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 14 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 13 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 17 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 11 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 14 | BAD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 14 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 14 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 15 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 16 | BAD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 12 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 14 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 12 | BAD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 15 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 12 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 10 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 12 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 15 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 12 | BAD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 10 | BAD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 15 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 12 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 12 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 11 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 12 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 15 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 14 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 17 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 14 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 10 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 16 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 12 | GOOD_SUCCESS | view → |
The task as the agent saw it and the verifier graded it. The reference solution/ is included below for transparency.