| Shell | Model | Backend | Hash | Format | Test | Status | Reason | Trajectory | Invoked | Match | Warmup (s) | Measured (s) | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gptme | local/ministral-3:8b | ollama | 1922accd5827ebe6829e536369195db25eaf664528dc66206d646ea3bb386b71 | tool | JSON Rank From File | PASS | clean | yes | 100% | 55.635 | 17.952 | details | |
| gptme | local/ministral-3:8b | ollama | 1922accd5827ebe6829e536369195db25eaf664528dc66206d646ea3bb386b71 | tool | Web Fetch JSON Raw | PASS | recovered | yes | 100% | 15.098 | 14.898 | details | |
| gptme | local/ministral-3:8b | ollama | 1922accd5827ebe6829e536369195db25eaf664528dc66206d646ea3bb386b71 | tool | Web Search JSON Ranked | FAIL | clean | yes | 0% | 99.381 | 16.749 | details |