fischer-agentkit/test-results/benchmark/baseline.json

1522 lines
42 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.

{
"timestamp": "2026-06-17T03:54:43.123142+00:00",
"version": "0.1.0",
"runs": 1,
"fast": false,
"overall_accuracy": 1.0,
"overall_accuracy_mean": 1.0,
"overall_accuracy_std": 0.0,
"summary": "All 53 tests passed across 7 dimensions.",
"dimensions": {
"preprocessing": {
"metrics": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.016,
"latency_p95_ms": 0.4208,
"latency_p99_ms": 1.1294,
"consistency": 1.0,
"total": 15,
"passed": 15,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.7961,
"ci_upper": 1.0
},
"by_category": {
"greeting": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0196,
"latency_p95_ms": 0.0241,
"latency_p99_ms": 0.0243,
"consistency": 1.0,
"total": 4,
"passed": 4,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5101,
"ci_upper": 1.0
},
"tool_query": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0153,
"latency_p95_ms": 0.0162,
"latency_p99_ms": 0.0164,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"skill_prefix": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0412,
"latency_p95_ms": 1.1801,
"latency_p99_ms": 1.2813,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
},
"complex": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0147,
"latency_p95_ms": 0.0148,
"latency_p99_ms": 0.0148,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.017,
"latency_p95_ms": 0.0239,
"latency_p99_ms": 0.0243,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"medium": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0156,
"latency_p95_ms": 0.0367,
"latency_p99_ms": 0.0403,
"consistency": 1.0,
"total": 7,
"passed": 7,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6457,
"ci_upper": 1.0
},
"hard": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0147,
"latency_p95_ms": 1.1774,
"latency_p99_ms": 1.2808,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "prep-001",
"dimension": "preprocessing",
"category": "greeting",
"difficulty": "easy",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.0221,
"root_cause": "none",
"detail": "input='你好' method=regex_direct",
"consistency": 1.0
},
{
"task_id": "prep-002",
"dimension": "preprocessing",
"category": "greeting",
"difficulty": "easy",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.0244,
"root_cause": "none",
"detail": "input='hello' method=regex_direct",
"consistency": 1.0
},
{
"task_id": "prep-003",
"dimension": "preprocessing",
"category": "greeting",
"difficulty": "easy",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.017,
"root_cause": "none",
"detail": "input='谢谢' method=regex_direct",
"consistency": 1.0
},
{
"task_id": "prep-004",
"dimension": "preprocessing",
"category": "greeting",
"difficulty": "easy",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.016,
"root_cause": "none",
"detail": "input='你是谁' method=regex_direct",
"consistency": 1.0
},
{
"task_id": "prep-005",
"dimension": "preprocessing",
"category": "tool_query",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0164,
"root_cause": "none",
"detail": "input='搜索golang教程' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-006",
"dimension": "preprocessing",
"category": "tool_query",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0156,
"root_cause": "none",
"detail": "input='执行ls命令' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-007",
"dimension": "preprocessing",
"category": "tool_query",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0153,
"root_cause": "none",
"detail": "input='翻译hello为中文' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-008",
"dimension": "preprocessing",
"category": "tool_query",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.014,
"root_cause": "none",
"detail": "input='什么是机器学习' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-009",
"dimension": "preprocessing",
"category": "tool_query",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0148,
"root_cause": "none",
"detail": "input='帮我分析数据' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-010",
"dimension": "preprocessing",
"category": "skill_prefix",
"difficulty": "medium",
"passed": true,
"expected": "skill_react",
"actual": "skill_react",
"duration_ms": 0.0412,
"root_cause": "none",
"detail": "input='@skill:react_agent 查看ip' method=skill_prefix",
"consistency": 1.0
},
{
"task_id": "prep-011",
"dimension": "preprocessing",
"category": "skill_prefix",
"difficulty": "medium",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.0262,
"root_cause": "none",
"detail": "input='@skill:chat_only 你好' method=skill_prefix",
"consistency": 1.0
},
{
"task_id": "prep-012",
"dimension": "preprocessing",
"category": "skill_prefix",
"difficulty": "hard",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 1.3066,
"root_cause": "none",
"detail": "input='@skill:nonexistent 做点什么' method=skill_not_found_fallback",
"consistency": 1.0
},
{
"task_id": "prep-013",
"dimension": "preprocessing",
"category": "complex",
"difficulty": "hard",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0147,
"root_cause": "none",
"detail": "input='帮我分析这个数据并生成报告' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-014",
"dimension": "preprocessing",
"category": "complex",
"difficulty": "easy",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0148,
"root_cause": "none",
"detail": "input='随便聊聊' method=default_react",
"consistency": 1.0
},
{
"task_id": "prep-015",
"dimension": "preprocessing",
"category": "complex",
"difficulty": "hard",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0132,
"root_cause": "none",
"detail": "input='请帮我完成以下任务1. 查询天气 2. 生成报告' method=default_react",
"consistency": 1.0
}
]
},
"overfitting": {
"metrics": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0295,
"latency_p95_ms": 0.0396,
"latency_p99_ms": 0.0401,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"by_category": {
"ip_check": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0402,
"latency_p95_ms": 0.0402,
"latency_p99_ms": 0.0402,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"search": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0282,
"latency_p95_ms": 0.0282,
"latency_p99_ms": 0.0282,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"greeting": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0373,
"latency_p95_ms": 0.0373,
"latency_p99_ms": 0.0373,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"tool_use": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0295,
"latency_p95_ms": 0.0295,
"latency_p99_ms": 0.0295,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"complex": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0249,
"latency_p95_ms": 0.0249,
"latency_p99_ms": 0.0249,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
}
},
"by_difficulty": {
"medium": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0295,
"latency_p95_ms": 0.0391,
"latency_p99_ms": 0.04,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
},
"easy": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0373,
"latency_p95_ms": 0.0373,
"latency_p99_ms": 0.0373,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"hard": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0249,
"latency_p95_ms": 0.0249,
"latency_p99_ms": 0.0249,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "over-001",
"dimension": "overfitting",
"category": "ip_check",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0402,
"root_cause": "none",
"detail": "paraphrases=5 modes=['react', 'react', 'react', 'react', 'react']",
"consistency": 1.0
},
{
"task_id": "over-002",
"dimension": "overfitting",
"category": "search",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0282,
"root_cause": "none",
"detail": "paraphrases=3 modes=['react', 'react', 'react']",
"consistency": 1.0
},
{
"task_id": "over-003",
"dimension": "overfitting",
"category": "greeting",
"difficulty": "easy",
"passed": true,
"expected": "direct_chat",
"actual": "direct_chat",
"duration_ms": 0.0373,
"root_cause": "none",
"detail": "paraphrases=5 modes=['direct_chat', 'direct_chat', 'direct_chat', 'direct_chat', 'direct_chat']",
"consistency": 1.0
},
{
"task_id": "over-004",
"dimension": "overfitting",
"category": "tool_use",
"difficulty": "medium",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0295,
"root_cause": "none",
"detail": "paraphrases=3 modes=['react', 'react', 'react']",
"consistency": 1.0
},
{
"task_id": "over-005",
"dimension": "overfitting",
"category": "complex",
"difficulty": "hard",
"passed": true,
"expected": "react",
"actual": "react",
"duration_ms": 0.0249,
"root_cause": "none",
"detail": "paraphrases=3 modes=['react', 'react', 'react']",
"consistency": 1.0
}
]
},
"efficiency": {
"metrics": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.33,
"latency_p95_ms": 0.602,
"latency_p99_ms": 0.6404,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"by_category": {
"preprocess_latency": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.33,
"latency_p95_ms": 0.402,
"latency_p99_ms": 0.4084,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
},
"tool_search_latency": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.345,
"latency_p95_ms": 0.6195,
"latency_p99_ms": 0.6439,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.16,
"latency_p95_ms": 0.268,
"latency_p99_ms": 0.2776,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
},
"medium": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.41,
"latency_p95_ms": 0.626,
"latency_p99_ms": 0.6452,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "eff-001",
"dimension": "efficiency",
"category": "preprocess_latency",
"difficulty": "easy",
"passed": true,
"expected": "<=50ms",
"actual": "0.003ms",
"duration_ms": 0.28,
"root_cause": "none",
"detail": "iterations=100 avg=0.003ms threshold=50.0ms",
"consistency": 1.0
},
{
"task_id": "eff-002",
"dimension": "efficiency",
"category": "preprocess_latency",
"difficulty": "medium",
"passed": true,
"expected": "<=50ms",
"actual": "0.003ms",
"duration_ms": 0.33,
"root_cause": "none",
"detail": "iterations=100 avg=0.003ms threshold=50.0ms",
"consistency": 1.0
},
{
"task_id": "eff-003",
"dimension": "efficiency",
"category": "preprocess_latency",
"difficulty": "medium",
"passed": true,
"expected": "<=50ms",
"actual": "0.004ms",
"duration_ms": 0.41,
"root_cause": "none",
"detail": "iterations=100 avg=0.004ms threshold=50.0ms",
"consistency": 1.0
},
{
"task_id": "eff-004",
"dimension": "efficiency",
"category": "tool_search_latency",
"difficulty": "medium",
"passed": true,
"expected": "<=10ms",
"actual": "0.006ms",
"duration_ms": 0.65,
"root_cause": "none",
"detail": "iterations=100 avg=0.006ms threshold=10.0ms",
"consistency": 1.0
},
{
"task_id": "eff-005",
"dimension": "efficiency",
"category": "tool_search_latency",
"difficulty": "easy",
"passed": true,
"expected": "<=5ms",
"actual": "0.000ms",
"duration_ms": 0.04,
"root_cause": "none",
"detail": "iterations=100 avg=0.000ms threshold=5.0ms",
"consistency": 1.0
}
]
},
"tool_search": {
"metrics": {
"accuracy": 1.0,
"precision": 0.8333,
"recall": 0.8333,
"f1": 0.8333,
"latency_p50_ms": 0.0229,
"latency_p95_ms": 0.0415,
"latency_p99_ms": 0.0518,
"consistency": 1.0,
"total": 10,
"passed": 10,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.7225,
"ci_upper": 1.0
},
"by_category": {
"exact_match": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0234,
"latency_p95_ms": 0.0487,
"latency_p99_ms": 0.0533,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"fuzzy_match": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0224,
"latency_p95_ms": 0.0228,
"latency_p99_ms": 0.0228,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
},
"no_match": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.0089,
"latency_p95_ms": 0.0141,
"latency_p99_ms": 0.0146,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
},
"top_k": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0184,
"latency_p95_ms": 0.0184,
"latency_p99_ms": 0.0184,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 0.8333,
"recall": 0.8333,
"f1": 0.8333,
"latency_p50_ms": 0.0231,
"latency_p95_ms": 0.0458,
"latency_p99_ms": 0.0527,
"consistency": 1.0,
"total": 7,
"passed": 7,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6457,
"ci_upper": 1.0
},
"medium": {
"accuracy": 1.0,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"latency_p50_ms": 0.0219,
"latency_p95_ms": 0.0227,
"latency_p99_ms": 0.0228,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "ts-001",
"dimension": "tool_search",
"category": "exact_match",
"difficulty": "easy",
"passed": true,
"expected": "read_file",
"actual": "read_file",
"duration_ms": 0.023,
"root_cause": "none",
"detail": "query='read file' top_k=5 results=2",
"consistency": 1.0
},
{
"task_id": "ts-002",
"dimension": "tool_search",
"category": "exact_match",
"difficulty": "easy",
"passed": true,
"expected": "write_file",
"actual": "write_file",
"duration_ms": 0.0544,
"root_cause": "none",
"detail": "query='write file content' top_k=5 results=2",
"consistency": 1.0
},
{
"task_id": "ts-003",
"dimension": "tool_search",
"category": "exact_match",
"difficulty": "easy",
"passed": true,
"expected": "web_search",
"actual": "web_search",
"duration_ms": 0.0258,
"root_cause": "none",
"detail": "query='search web information' top_k=5 results=2",
"consistency": 1.0
},
{
"task_id": "ts-004",
"dimension": "tool_search",
"category": "exact_match",
"difficulty": "easy",
"passed": true,
"expected": "shell_exec",
"actual": "shell_exec",
"duration_ms": 0.0234,
"root_cause": "none",
"detail": "query='execute shell command' top_k=5 results=1",
"consistency": 1.0
},
{
"task_id": "ts-005",
"dimension": "tool_search",
"category": "exact_match",
"difficulty": "easy",
"passed": true,
"expected": "http_request",
"actual": "http_request",
"duration_ms": 0.0231,
"root_cause": "none",
"detail": "query='send http request url' top_k=5 results=1",
"consistency": 1.0
},
{
"task_id": "ts-006",
"dimension": "tool_search",
"category": "fuzzy_match",
"difficulty": "medium",
"passed": true,
"expected": "read_file",
"actual": "read_file",
"duration_ms": 0.0228,
"root_cause": "none",
"detail": "query='io file' top_k=5 results=2",
"consistency": 1.0
},
{
"task_id": "ts-007",
"dimension": "tool_search",
"category": "fuzzy_match",
"difficulty": "medium",
"passed": true,
"expected": "web_search",
"actual": "web_search",
"duration_ms": 0.0219,
"root_cause": "none",
"detail": "query='search query engine' top_k=5 results=1",
"consistency": 1.0
},
{
"task_id": "ts-008",
"dimension": "tool_search",
"category": "no_match",
"difficulty": "easy",
"passed": true,
"expected": "__none__",
"actual": "[]",
"duration_ms": 0.003,
"root_cause": "none",
"detail": "query='' top_k=5 results=0",
"consistency": 1.0
},
{
"task_id": "ts-009",
"dimension": "tool_search",
"category": "no_match",
"difficulty": "easy",
"passed": true,
"expected": "__none__",
"actual": "[]",
"duration_ms": 0.0147,
"root_cause": "none",
"detail": "query='zzzznonexistent' top_k=5 results=0",
"consistency": 1.0
},
{
"task_id": "ts-010",
"dimension": "tool_search",
"category": "top_k",
"difficulty": "medium",
"passed": true,
"expected": "read_file",
"actual": "read_file",
"duration_ms": 0.0184,
"root_cause": "none",
"detail": "query='file' top_k=1 results=1",
"consistency": 1.0
}
]
},
"event_model": {
"metrics": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.0894,
"latency_p95_ms": 16.7933,
"latency_p99_ms": 20.5773,
"consistency": 1.0,
"total": 6,
"passed": 6,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6097,
"ci_upper": 1.0
},
"by_category": {
"sq_lifecycle": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.0671,
"latency_p95_ms": 0.1071,
"latency_p99_ms": 0.1107,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
},
"eq_lifecycle": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 2.6035,
"latency_p95_ms": 19.6313,
"latency_p99_ms": 21.1449,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.0894,
"latency_p95_ms": 16.7933,
"latency_p99_ms": 20.5773,
"consistency": 1.0,
"total": 6,
"passed": 6,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6097,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "ev-001",
"dimension": "event_model",
"category": "sq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "drained=['hello']",
"duration_ms": 0.1116,
"root_cause": "none",
"detail": "task_id=5c4be886...",
"consistency": 1.0
},
{
"task_id": "ev-002",
"dimension": "event_model",
"category": "sq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "cancelled=True",
"duration_ms": 0.0671,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "ev-003",
"dimension": "event_model",
"category": "sq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "raised=True closed=True",
"duration_ms": 0.0143,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "ev-004",
"dimension": "event_model",
"category": "eq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "received=1",
"duration_ms": 2.6035,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "ev-005",
"dimension": "event_model",
"category": "eq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "events=1 closed=True",
"duration_ms": 21.5233,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "ev-006",
"dimension": "event_model",
"category": "eq_lifecycle",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "subscribers=0",
"duration_ms": 0.008,
"root_cause": "none",
"detail": "",
"consistency": 1.0
}
]
},
"spec_management": {
"metrics": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 1.4329,
"latency_p95_ms": 2.75,
"latency_p99_ms": 3.1046,
"consistency": 1.0,
"total": 7,
"passed": 7,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6457,
"ci_upper": 1.0
},
"by_category": {
"crud": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 1.4329,
"latency_p95_ms": 2.8609,
"latency_p99_ms": 3.1268,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"edge": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 0.8834,
"latency_p95_ms": 1.6324,
"latency_p99_ms": 1.699,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 1.3287,
"latency_p95_ms": 2.7777,
"latency_p99_ms": 3.1102,
"consistency": 1.0,
"total": 6,
"passed": 6,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.6097,
"ci_upper": 1.0
},
"medium": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 1.7156,
"latency_p95_ms": 1.7156,
"latency_p99_ms": 1.7156,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "sm-001",
"dimension": "spec_management",
"category": "crud",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "exists=True",
"duration_ms": 1.4329,
"root_cause": "none",
"detail": "path=/var/folders/6b/ljk5bdq50yxcsth24frf05200000gn/T/agentkit-benchmark-dzm9kg48/run-0/specs/sm-001/test-spec.yaml",
"consistency": 1.0
},
{
"task_id": "sm-002",
"dimension": "spec_management",
"category": "crud",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "steps=2",
"duration_ms": 1.2244,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "sm-003",
"dimension": "spec_management",
"category": "crud",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "goal=Updated goal",
"duration_ms": 1.5311,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "sm-004",
"dimension": "spec_management",
"category": "crud",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "deleted=True remaining=0",
"duration_ms": 1.1484,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "sm-005",
"dimension": "spec_management",
"category": "crud",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "count=2",
"duration_ms": 3.1933,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "sm-006",
"dimension": "spec_management",
"category": "edge",
"difficulty": "medium",
"passed": true,
"expected": "passed",
"actual": "status=confirmed",
"duration_ms": 1.7156,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "sm-007",
"dimension": "spec_management",
"category": "edge",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "result=None",
"duration_ms": 0.0512,
"root_cause": "none",
"detail": "",
"consistency": 1.0
}
]
},
"verification": {
"metrics": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 24.8909,
"latency_p95_ms": 411.9118,
"latency_p99_ms": 487.0974,
"consistency": 1.0,
"total": 5,
"passed": 5,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.5655,
"ci_upper": 1.0
},
"by_category": {
"basic": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 11.7309,
"latency_p95_ms": 11.9356,
"latency_p99_ms": 11.9538,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
},
"retry": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 35.984,
"latency_p95_ms": 35.984,
"latency_p99_ms": 35.984,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"timeout": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 505.8938,
"latency_p95_ms": 505.8938,
"latency_p99_ms": 505.8938,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
},
"multi": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 24.8909,
"latency_p95_ms": 24.8909,
"latency_p99_ms": 24.8909,
"consistency": 1.0,
"total": 1,
"passed": 1,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.2065,
"ci_upper": 1.0
}
},
"by_difficulty": {
"easy": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 11.7309,
"latency_p95_ms": 11.9356,
"latency_p99_ms": 11.9538,
"consistency": 1.0,
"total": 2,
"passed": 2,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.3424,
"ci_upper": 1.0
},
"medium": {
"accuracy": 1.0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"latency_p50_ms": 35.984,
"latency_p95_ms": 458.9028,
"latency_p99_ms": 496.4956,
"consistency": 1.0,
"total": 3,
"passed": 3,
"failed": 0,
"accuracy_mean": 1.0,
"accuracy_std": 0.0,
"ci_lower": 0.4385,
"ci_upper": 1.0
}
},
"cases": [
{
"task_id": "vf-001",
"dimension": "verification",
"category": "basic",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "passed=True attempts=1",
"duration_ms": 11.5036,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "vf-002",
"dimension": "verification",
"category": "basic",
"difficulty": "easy",
"passed": true,
"expected": "passed",
"actual": "passed=False errors=1",
"duration_ms": 11.9583,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "vf-003",
"dimension": "verification",
"category": "retry",
"difficulty": "medium",
"passed": true,
"expected": "passed",
"actual": "attempts=3 callbacks=2",
"duration_ms": 35.984,
"root_cause": "none",
"detail": "",
"consistency": 1.0
},
{
"task_id": "vf-004",
"dimension": "verification",
"category": "timeout",
"difficulty": "medium",
"passed": true,
"expected": "passed",
"actual": "passed=False errors=1",
"duration_ms": 505.8938,
"root_cause": "none",
"detail": "errors=['Command timed out after 0.5s: sleep 10']",
"consistency": 1.0
},
{
"task_id": "vf-005",
"dimension": "verification",
"category": "multi",
"difficulty": "medium",
"passed": true,
"expected": "passed",
"actual": "passed=False",
"duration_ms": 24.8909,
"root_cause": "none",
"detail": "",
"consistency": 1.0
}
]
}
}
}