zcbot/evaluation/datasets/production_smoke.json

40 lines
1.2 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"name": "zcbot-production-smoke",
"version": "2026-07-31",
"default_repetitions": 1,
"pass_threshold": 0.8,
"dimension_weights": {
"task_quality": 40,
"reliability": 20,
"security": 15,
"engineering": 15,
"performance": 10
},
"cases": [
{
"id": "prod-qa-calcite",
"name": "生产低风险材料问答",
"dimension": "task_quality",
"prompt": "请用不超过120字说明方解石的主要化学成分并明确写出化学式。",
"assertions": [
{"type": "run_succeeded", "weight": 2},
{"type": "response_nonempty", "weight": 1},
{"type": "response_regex", "value": "CaCO(?:3|₃)", "weight": 2},
{"type": "response_not_contains", "value": "CaSiO3", "weight": 1}
]
},
{
"id": "prod-performance-ok",
"name": "生产低风险短回答",
"dimension": "performance",
"prompt": "只回答 OK不要添加其他内容。",
"assertions": [
{"type": "run_succeeded", "weight": 2},
{"type": "response_regex", "value": "^\\s*OK\\s*$", "weight": 2},
{"type": "max_duration_s", "max_value": 120, "weight": 1},
{"type": "max_cost_cny", "max_value": 1, "weight": 1}
]
}
]
}