- 入库历史遗漏源码/测试:router_system 9 模块(agent/executors/inference/knowledge/ memory/planner/skills/trace)、tests 11 个测试文件、config/knowledge 领域知识 - 入库根目录方案文档(v2/v3/可行性×2)、references 文献(arxiv 14-18/cnki_open/ 参考文献清单)、research 论文素材(routerarena/paper/中文文献 PDF) - 前端构建产物刷新(新 hash);webapp 误写文档删除 - gitignore 增补:deepseek-harness、research/_refs、.mimosa/.zcode、网关日志/pid、 临时调试脚本、tests/e2e/node_modules、AI代理功能开发/prefix - 基线确认:318 passed
1686 lines
40 KiB
JSON
1686 lines
40 KiB
JSON
[
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "algorithm",
|
|
"subdomain2": "sorting",
|
|
"difficulty": "medium",
|
|
"confidence": 0.8504,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0000",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:code@0.59/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0001",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "debugging",
|
|
"subdomain2": "error-analysis",
|
|
"difficulty": "hard",
|
|
"confidence": 0.9631,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0002",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "database",
|
|
"subdomain2": "sql",
|
|
"difficulty": "hard",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:code@0.55/hard",
|
|
"subdomain:database",
|
|
"subdomain2:sql",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0003",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "algorithm",
|
|
"subdomain2": "sorting",
|
|
"difficulty": "medium",
|
|
"confidence": 0.6988,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0004",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "algorithm",
|
|
"subdomain2": "sorting",
|
|
"difficulty": "easy",
|
|
"confidence": 0.9502,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:implement",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0005",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "debugging",
|
|
"subdomain2": "error-analysis",
|
|
"difficulty": "easy",
|
|
"confidence": 0.99,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0006",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "database",
|
|
"subdomain2": "sql",
|
|
"difficulty": "medium",
|
|
"confidence": 0.8997,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0007",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": "algorithm",
|
|
"subdomain2": "sorting",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5034,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:code@0.50/medium",
|
|
"subdomain:algorithm",
|
|
"subdomain2:sorting",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0008",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.6988,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:implement",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0009",
|
|
"ground_truth_domain": "code"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0010",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "proof",
|
|
"subdomain2": "proof",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:math@0.59/medium",
|
|
"subdomain:proof",
|
|
"subdomain2:proof",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0011",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "calculus",
|
|
"subdomain2": "calculus",
|
|
"difficulty": "hard",
|
|
"confidence": 0.6321,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:math:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0012",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "algebra",
|
|
"subdomain2": "equation",
|
|
"difficulty": "easy",
|
|
"confidence": 0.6321,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:math:solve",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0013",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "geometry",
|
|
"subdomain2": "geometry",
|
|
"difficulty": "medium",
|
|
"confidence": 0.8173,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:math:verify",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0014",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "general",
|
|
"subdomain2": "math-general",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:math@0.55/medium",
|
|
"subdomain:general",
|
|
"subdomain2:math-general",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0015",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "math",
|
|
"subdomain": "algebra",
|
|
"subdomain2": "algebra",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:math@0.59/easy",
|
|
"subdomain:algebra",
|
|
"subdomain2:algebra",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0016",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0017",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0018",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0019",
|
|
"ground_truth_domain": "math"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "contract",
|
|
"subdomain2": "contract",
|
|
"difficulty": "easy",
|
|
"confidence": 0.4681,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:legal@0.47/easy",
|
|
"subdomain:contract",
|
|
"subdomain2:contract",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0020",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0021",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "contract",
|
|
"subdomain2": "contract",
|
|
"difficulty": "easy",
|
|
"confidence": 0.6321,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:legal:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0022",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "labor",
|
|
"subdomain2": "labor",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8504,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:legal:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0023",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "contract",
|
|
"subdomain2": "contract",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:legal@0.59/easy",
|
|
"subdomain:contract",
|
|
"subdomain2:contract",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0024",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0025",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0026",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "contract",
|
|
"subdomain2": "contract",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8647,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:legal:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0027",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "legal",
|
|
"subdomain": "contract",
|
|
"subdomain2": "contract",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5373,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:legal@0.54/medium",
|
|
"subdomain:contract",
|
|
"subdomain2:contract",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0028",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0029",
|
|
"ground_truth_domain": "legal"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:medical@0.59/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0030",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "firstaid",
|
|
"subdomain2": "first-aid",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:medical@0.59/easy",
|
|
"subdomain:firstaid",
|
|
"subdomain2:first-aid",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0031",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "chronic",
|
|
"subdomain2": "hypertension",
|
|
"difficulty": "easy",
|
|
"confidence": 0.9392,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:medical:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0032",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "medication",
|
|
"subdomain2": "medication",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8504,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:medical:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0033",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:medical@0.59/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0034",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0035",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "firstaid",
|
|
"subdomain2": "first-aid",
|
|
"difficulty": "easy",
|
|
"confidence": 0.6321,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:medical:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0036",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "common",
|
|
"subdomain2": "common-illness",
|
|
"difficulty": "medium",
|
|
"confidence": 0.8504,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:medical:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0037",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0038",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "medical",
|
|
"subdomain": "chronic",
|
|
"subdomain2": "chronic-disease",
|
|
"difficulty": "easy",
|
|
"confidence": 0.6321,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:medical:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0039",
|
|
"ground_truth_domain": "medical"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "investing",
|
|
"subdomain2": "investing",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:finance@0.55/medium",
|
|
"subdomain:investing",
|
|
"subdomain2:investing",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0040",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "credit",
|
|
"subdomain2": "credit",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:finance@0.59/easy",
|
|
"subdomain:credit",
|
|
"subdomain2:credit",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0041",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "investing",
|
|
"subdomain2": "investing",
|
|
"difficulty": "easy",
|
|
"confidence": 0.9392,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:finance:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0042",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "credit",
|
|
"subdomain2": "credit",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8504,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:finance:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0043",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "loan",
|
|
"subdomain2": "loan",
|
|
"difficulty": "easy",
|
|
"confidence": 0.9328,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:finance:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0044",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "loan",
|
|
"subdomain2": "loan",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8173,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:finance:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0045",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0046",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "investing",
|
|
"subdomain2": "investing",
|
|
"difficulty": "medium",
|
|
"confidence": 0.8647,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:finance:disclaimer",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "claude-3-haiku-20240307",
|
|
"global_index": "mock_0047",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "finance",
|
|
"subdomain": "investing",
|
|
"subdomain2": "investing",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:professional@auto",
|
|
"classify:finance@0.59/medium",
|
|
"subdomain:investing",
|
|
"subdomain2:investing",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0048",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0049",
|
|
"ground_truth_domain": "finance"
|
|
},
|
|
{
|
|
"domain": "life",
|
|
"subdomain": "travel",
|
|
"subdomain2": "travel",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:life@0.59/easy",
|
|
"subdomain:travel",
|
|
"subdomain2:travel",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0050",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0051",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "life",
|
|
"subdomain": "travel",
|
|
"subdomain2": "travel",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8173,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:life:advise",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gemini-2.0-flash-001",
|
|
"global_index": "mock_0052",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "life",
|
|
"subdomain": "fitness",
|
|
"subdomain2": "fitness",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8347,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:life:advise",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gemini-2.0-flash-001",
|
|
"global_index": "mock_0053",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0054",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0055",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0056",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "life",
|
|
"subdomain": "fitness",
|
|
"subdomain2": "fitness",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:life@0.59/easy",
|
|
"subdomain:fitness",
|
|
"subdomain2:fitness",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0057",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0058",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0059",
|
|
"ground_truth_domain": "life"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "exam",
|
|
"subdomain2": "exam",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5934,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:education@0.59/medium",
|
|
"subdomain:exam",
|
|
"subdomain2:exam",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0060",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "study",
|
|
"subdomain2": "study-method",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:education@0.55/easy",
|
|
"subdomain:study",
|
|
"subdomain2:study-method",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0061",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "exam",
|
|
"subdomain2": "exam",
|
|
"difficulty": "easy",
|
|
"confidence": 0.9328,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:education:design",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "deepseek-chat",
|
|
"global_index": "mock_0062",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "study",
|
|
"subdomain2": "study-method",
|
|
"difficulty": "easy",
|
|
"confidence": 0.8647,
|
|
"quality_score": 1.0,
|
|
"upgraded": false,
|
|
"model_used": "rule:education:design",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "deepseek-chat",
|
|
"global_index": "mock_0063",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "career",
|
|
"subdomain2": "career",
|
|
"difficulty": "easy",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:education@0.55/easy",
|
|
"subdomain:career",
|
|
"subdomain2:career",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0064",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0065",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0066",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "education",
|
|
"subdomain": "career",
|
|
"subdomain2": "career",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5507,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:lifestyle@auto",
|
|
"classify:education@0.55/medium",
|
|
"subdomain:career",
|
|
"subdomain2:career",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0067",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.6988,
|
|
"quality_score": 0.97,
|
|
"upgraded": false,
|
|
"model_used": "rule:code:implement",
|
|
"route": [
|
|
"cache:exact"
|
|
],
|
|
"selected_slot": "gpt-4o-mini",
|
|
"global_index": "mock_0068",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0069",
|
|
"ground_truth_domain": "education"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0070",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "medium",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/medium",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0071",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0072",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.3297,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.33/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0073",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0074",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0075",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "writing",
|
|
"subdomain2": "writing",
|
|
"difficulty": "easy",
|
|
"confidence": 0.3297,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.33/easy",
|
|
"subdomain:writing",
|
|
"subdomain2:writing",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0076",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0077",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.2592,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.26/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0078",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": "explain",
|
|
"subdomain2": "explain",
|
|
"difficulty": "easy",
|
|
"confidence": 0.3297,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.33/easy",
|
|
"subdomain:explain",
|
|
"subdomain2:explain",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0079",
|
|
"ground_truth_domain": "general"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0080",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0081",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0082",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0083",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0084",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0085",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0086",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "medium",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/medium",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0087",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "general",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:general@auto",
|
|
"classify:general@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0088",
|
|
"ground_truth_domain": "creative"
|
|
},
|
|
{
|
|
"domain": "code",
|
|
"subdomain": null,
|
|
"subdomain2": null,
|
|
"difficulty": "easy",
|
|
"confidence": 0.5034,
|
|
"quality_score": 0.0,
|
|
"upgraded": true,
|
|
"model_used": "deepseek-chat",
|
|
"route": [
|
|
"cache:miss",
|
|
"group:tech@auto",
|
|
"classify:code@0.50/easy",
|
|
"direct_fallback"
|
|
],
|
|
"selected_slot": "mistral-medium",
|
|
"global_index": "mock_0089",
|
|
"ground_truth_domain": "creative"
|
|
}
|
|
] |