chore: expand cli semantic benchmark coverage
This commit is contained in:
1 parent
d1dbc27031
commit
a3f5585700
4 files changed
+121
-5
No files matched your search
@@ -17,3 +17,7 @@
|
||||
{"type":"config","name":"dynamic-chat-templates-variants","metricName":"template_score","metricUnit":"%","bestDirection":"higher"}
|
||||
{"run":13,"commit":"ffab766","metric":90.909,"metrics":{"passed_cases":10,"failed_cases":1,"total_cases":11},"status":"keep","description":"baseline","timestamp":1774560738,"segment":4}
|
||||
{"run":14,"commit":"f200733","metric":100.0,"metrics":{"passed_cases":11,"failed_cases":0,"total_cases":11},"status":"keep","description":"detect moonshot as kimi family","timestamp":1774560829,"segment":4}
|
||||
{"type":"config","name":"localllm-cli-control-surface","metricName":"cli_surface_score","metricUnit":"%","bestDirection":"higher"}
|
||||
{"run":15,"commit":"fd773a9","metric":18.182,"metrics":{"passed_cases":2,"failed_cases":9,"total_cases":11},"status":"keep","description":"baseline","timestamp":1774562027,"segment":5}
|
||||
{"run":16,"commit":"70cc59a","metric":100.0,"metrics":{"passed_cases":11,"failed_cases":0,"total_cases":11},"status":"keep","description":"expand cli command surface","timestamp":1774562138,"segment":5}
|
||||
{"type":"config","name":"localllm-cli-semantic-contracts","metricName":"cli_surface_score","metricUnit":"%","bestDirection":"higher"}
|
||||
Reference in new issue
Block a user