core/evals/capability_index/baseline.json

38 lines
821 B
JSON

{
"capability_score": 0.919641,
"coverage_geomean": 0.919641,
"coverage_micro": 0.995962,
"accuracy_micro": 1.0,
"breadth": 3,
"min_domain_coverage": 0.833333,
"wrong_total": 0,
"assert_mode_valid": true,
"deterministic_digest": "115389d285babb5980b8b31c40d3a1c58ded1e1f9ae08ec428090bba18d42ed0",
"domains": [
{
"domain": "deductive_logic",
"correct": 716,
"wrong": 0,
"refused": 0,
"coverage": 1.0,
"accuracy": 1.0
},
{
"domain": "dimensional",
"correct": 10,
"wrong": 0,
"refused": 2,
"coverage": 0.833333,
"accuracy": 1.0
},
{
"domain": "relational_metric",
"correct": 14,
"wrong": 0,
"refused": 1,
"coverage": 0.933333,
"accuracy": 1.0
}
],
"not_covered": []
}