| CLI Agent | Model | Backend | Hash | Format | Test | Status | Reason | Trajectory | Invoked | Match | Warmup (s) | Measured (s) | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| codex 0.128.0 | local/aravhawk/qwen3.5-opus-4.6-text:9b | ollama | 74348a6ec8d24b1098799494443e2455f8f77e630c6de078429d731b2647df65 | tool | JSON Rank From File | PASS | clean | yes | 100% | 64.546 | 21.491 | details | |
| codex 0.128.0 | local/aravhawk/qwen3.5-opus-4.6-text:9b | ollama | 74348a6ec8d24b1098799494443e2455f8f77e630c6de078429d731b2647df65 | tool | Patch File From Prepared Patch | FAIL | clean | yes | 0% | 44.121 | 90.692 | details |