| Agent | Model | Reward | Runtime | Tools | Classification | |
|---|---|---|---|---|---|---|
| claude-code | claude-sonnet-4-6 | ✗ failed | — | 25 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 270 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 272 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 271 | GOOD_SUCCESS | view → |
| claude-code | claude-sonnet-4-6 | ✗ failed | — | 49 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 273 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 275 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 238 | GOOD_SUCCESS | view → |
| claude-code | claude-sonnet-4-6 | ✗ failed | — | 300 | GOOD_FAILURE | view → |
| claude-code | claude-sonnet-4-6 | ✗ failed | — | 34 | GOOD_FAILURE | view → |
| claude-code | claude-sonnet-4-6 | ✗ failed | — | 27 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 210 | BAD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✗ failed | — | 270 | GOOD_FAILURE | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 219 | GOOD_SUCCESS | view → |
| claude-code | claude-opus-4-8 | ✓ resolved | — | 73 | GOOD_SUCCESS | view → |
The task as the agent saw it and the verifier graded it. The reference solution/ is included below for transparency.