bullshit-benchmark/config.v1.gpt-5.3-chat.gemini-3.1-flash-lite-preview.json at main · mtauraso/bullshit-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
{
  "collect": {
    "questions": "questions.json",
    "models": [
      "openai/gpt-5.3-chat",
      "google/gemini-3.1-flash-lite-preview"
    ],
    "models_file": "",
    "model_providers": {
      "*": "openrouter"
    },
    "num_runs": 1,
    "parallelism": 12,
    "techniques": "cross_domain_concept_stitching,inverted_nonexistent_dependency,false_granularity,misapplied_mechanism,reified_metaphor,plausible_nonexistent_framework,wrong_unit_of_analysis,temporal_category_error,causal_chimera,authoritative_framing_of_nothing",
    "temperature": null,
    "omit_response_system_prompt": true,
    "response_reasoning_effort": "off",
    "store_request_messages": false,
    "store_response_raw": true,
    "model_reasoning_efforts": {},
    "shuffle_tasks": true,
    "max_inflight_per_model": 2,
    "rate_limit_requeue": true,
    "rate_limit_cooldown_seconds": 20.0,
    "rate_limit_cooldown_max_seconds": 240.0,
    "rate_limit_cooldown_jitter_seconds": 1.5,
    "rate_limit_max_attempts": 20,
    "checkpoint_fsync_every": 10
  },
  "grade": {
    "judge_model": "anthropic/claude-sonnet-4.6",
    "model_providers": {
      "*": "openrouter"
    },
    "judge_models": [
      "anthropic/claude-sonnet-4.6",
      "openai/gpt-5.2",
      "google/gemini-3.1-pro-preview"
    ],
    "parallelism": 8,
    "judge_temperature": null,
    "judge_reasoning_effort": "medium",
    "judge_max_tokens": 0,
    "store_judge_response_raw": true,
    "judge_no_hint": true
  },
  "grade_panel": {
    "judge_models": [
      "anthropic/claude-sonnet-4.6",
      "openai/gpt-5.2",
      "google/gemini-3.1-pro-preview"
    ],
    "panel_mode": "full",
    "consensus_method": "mean",
    "parallel_primary_judges": true,
    "tiebreaker_model": ""
  }
}