| Shell | Model | Backend | Hash | Format | Test | Status | Reason | Trajectory | Invoked | Match | Warmup (s) | Measured (s) | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gptme | local/gemma4:e2b | ollama | 7fbdbf8f5e45a75bb122155ed546e765b4d9c53a1285f62fd9f506baa1c5a47e | tool | JSON Rank From File | FAIL | recovered | yes | 0% | 113.105 | 74.268 | details | |
| gptme | local/gemma4:e2b | ollama | 7fbdbf8f5e45a75bb122155ed546e765b4d9c53a1285f62fd9f506baa1c5a47e | tool | Web Fetch JSON Raw | PASS | recovered | yes | 100% | 34.887 | 38.797 | details | |
| gptme | local/gemma4:e2b | ollama | 7fbdbf8f5e45a75bb122155ed546e765b4d9c53a1285f62fd9f506baa1c5a47e | tool | Web Search JSON Ranked | FAIL | recovered | yes | 0% | 68.161 | 47.766 | details |