LLM-API-benchmark/test_results.json at main · inoutcode/LLM-API-benchmark · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
{
  "config": {
    "api": "openai",
    "url": "https://test.example.com",
    "model": "test-model",
    "parallel": 8,
    "number": 50
  },
  "test_time": "2026-04-12 17:05:50",
  "total_tests": 5,
  "results": [
    {
      "test_index": 1,
      "start_time": "2026-04-12 17:05:50",
      "end_time": "2026-04-12 17:07:50",
      "metrics": [
        {
          "concurrency": 10,
          "rate": "INF",
          "rps": 0.07,
          "avg_latency": 45.0,
          "p99_latency": 150.0,
          "avg_ttft": 1.4,
          "p99_ttft": 2.5,
          "avg_tpot": 0.024,
          "p99_tpot": 0.029,
          "gen_toks": 120.0,
          "success_rate": 100.0
        }
      ],
      "success": true,
      "error_message": ""
    },
    {
      "test_index": 2,
      "start_time": "2026-04-12 17:35:50",
      "end_time": "2026-04-12 17:37:50",
      "metrics": [
        {
          "concurrency": 10,
          "rate": "INF",
          "rps": 0.08,
          "avg_latency": 47.0,
          "p99_latency": 155.0,
          "avg_ttft": 1.5,
          "p99_ttft": 2.7,
          "avg_tpot": 0.024,
          "p99_tpot": 0.029,
          "gen_toks": 125.0,
          "success_rate": 100.0
        }
      ],
      "success": true,
      "error_message": ""
    },
    {
      "test_index": 3,
      "start_time": "2026-04-12 18:05:50",
      "end_time": "2026-04-12 18:07:50",
      "metrics": [
        {
          "concurrency": 10,
          "rate": "INF",
          "rps": 0.09000000000000001,
          "avg_latency": 49.0,
          "p99_latency": 160.0,
          "avg_ttft": 1.5999999999999999,
          "p99_ttft": 2.9,
          "avg_tpot": 0.024,
          "p99_tpot": 0.029,
          "gen_toks": 130.0,
          "success_rate": 100.0
        }
      ],
      "success": true,
      "error_message": ""
    },
    {
      "test_index": 4,
      "start_time": "2026-04-12 18:35:50",
      "end_time": "2026-04-12 18:37:50",
      "metrics": [
        {
          "concurrency": 10,
          "rate": "INF",
          "rps": 0.1,
          "avg_latency": 51.0,
          "p99_latency": 165.0,
          "avg_ttft": 1.7,
          "p99_ttft": 3.1,
          "avg_tpot": 0.024,
          "p99_tpot": 0.029,
          "gen_toks": 135.0,
          "success_rate": 100.0
        }
      ],
      "success": true,
      "error_message": ""
    },
    {
      "test_index": 5,
      "start_time": "2026-04-12 19:05:50",
      "end_time": "2026-04-12 19:07:50",
      "metrics": [
        {
          "concurrency": 10,
          "rate": "INF",
          "rps": 0.11000000000000001,
          "avg_latency": 53.0,
          "p99_latency": 170.0,
          "avg_ttft": 1.7999999999999998,
          "p99_ttft": 3.3,
          "avg_tpot": 0.024,
          "p99_tpot": 0.029,
          "gen_toks": 140.0,
          "success_rate": 100.0
        }
      ],
      "success": true,
      "error_message": ""
    }
  ]
}