public_evaluations/models.json at main · ByteBell/public_evaluations · 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
{
  "smoke_test_model": "xiaomi/mimo-v2-flash",
  "stress_test_model": "xiaomi/mimo-v2-flash",
  "judge_model": "anthropic/claude-sonnet-4.6",

  "models": {
    "openai/gpt-5.1-codex":{
      "input_cost_per_million_tokens": 1.25,
      "output_cost_per_million_tokens": 10

    },
    "qwen/qwen3-coder-next": {
      "input_cost_per_million_tokens": 0.12,
      "output_cost_per_million_tokens": 0.75

    },

    "x-ai/grok-code-fast-1": {
      "input_cost_per_million_tokens": 0.2,
      "output_cost_per_million_tokens": 1.5
    },
    "google/gemini-3.1-pro-preview": {
      "input_cost_per_million_tokens": 2,
      "output_cost_per_million_tokens": 12
  },
  "openai/gpt-5.2": {
      "input_cost_per_million_tokens": 1.75,
      "output_cost_per_million_tokens": 14
    },

    "anthropic/claude-sonnet-4.6": {
      "input_cost_per_million_tokens": 3,
      "output_cost_per_million_tokens": 15
    },
    "anthropic/claude-haiku-4.5": {
      "input_cost_per_million_tokens": 1,
      "output_cost_per_million_tokens": 5
    }

  }
}