live / results / 2026-08-26-google-gemma-4-26b-a4b-qat.md
live / results / 2026-08-26-google-gemma-4-26b-a4b-qat.md
Model: google/gemma-4-26b-a4b-qat
Driver: in-process ยท Context length: 16384
| Scenario | Result | Checks | Tool calls | Rounds | Invalid | Envelope | Wall (s) | Tokens (prompt/predicted) |
|---|---|---|---|---|---|---|---|---|
| S1 | โ | 6/6 | 12 | 13 | 0 | 0 | 11.3 | 80640/1414 |
| S3 | โ | 11/11 | 10 | 12 | 0 | 0 | 13.6 | 79786/1789 |
| S5 | โ | 2/3 | 9 | 10 | 0 | 0 | 9.9 | 52260/994 |
| S9 | โ | 7/11 | 4 | 6 | 1 | 0 | 62.8 | 26096/11803 |
โ ๏ธ = the run reached the context ceiling. Where the row still passes, the scored work had already completed and been written to disk before the model ran out of context; a longer task at the same context length would be cut off mid-work. Pair the plugin with a context compressor, or raise the context length.
Pass = every check ok. Checks assert filesystem, git and .agentic state, never model prose. Results are comparable only within one model.
Model: google/gemma-4-26b-a4b-qat
Driver: in-process ยท Context length: 16384
| Scenario | Result | Checks | Tool calls | Rounds | Invalid | Envelope | Wall (s) | Tokens (prompt/predicted) |
|---|---|---|---|---|---|---|---|---|
| S1 | โ | 6/6 | 12 | 13 | 0 | 0 | 11.3 | 80640/1414 |
| S3 | โ | 11/11 | 10 | 12 | 0 | 0 | 13.6 | 79786/1789 |
| S5 | โ | 2/3 | 9 | 10 | 0 | 0 | 9.9 | 52260/994 |
| S9 | โ | 7/11 | 4 | 6 | 1 | 0 | 62.8 | 26096/11803 |
โ ๏ธ = the run reached the context ceiling. Where the row still passes, the scored work had already completed and been written to disk before the model ran out of context; a longer task at the same context length would be cut off mid-work. Pair the plugin with a context compressor, or raise the context length.
Pass = every check ok. Checks assert filesystem, git and .agentic state, never model prose. Results are comparable only within one model.