{
  "model_name": "GPT-5.2",
  "model_organization": "OpenAI",
  "submitting_organization": "Sierra",
  "submission_date": "2026-02-26",
  "contact_info": {
    "email": "victor@sierra.ai, ben.s@sierra.ai",
    "name": "Sierra Research Team"
  },
  "is_new": false,
  "submission_type": "standard",
  "trajectories_available": true,
  "trajectory_files": {
    "airline": "gpt-5.2_none_airline_gpt-5.2_4trials.json",
    "retail": "gpt-5.2_none_retail_gpt-5.2_4trials.json",
    "telecom": "gpt-5.2_none_telecom_gpt-5.2_4trials.json",
    "banking_knowledge": "gpt-5.2_none_banking_knowledge_gpt-5.2_4trials.json"
  },
  "references": [],
  "results": {
    "airline": {
      "pass_1": 52.5,
      "pass_2": 35.66666666666667,
      "pass_3": 27.0,
      "pass_4": 22.0,
      "cost": 0.053692803500000004
    },
    "retail": {
      "pass_1": 75.0,
      "pass_2": 62.13450292397662,
      "pass_3": 53.07017543859649,
      "pass_4": 45.614035087719294,
      "cost": 0.048219267434210525
    },
    "telecom": {
      "pass_1": 57.23684210526315,
      "pass_2": 42.83625730994152,
      "pass_3": 35.526315789473685,
      "pass_4": 30.701754385964914,
      "cost": 0.04937742280701755
    },
    "banking_knowledge": {
      "pass_1": 12.63,
      "pass_2": 7.22,
      "pass_3": 5.15,
      "pass_4": 4.12,
      "cost": 0.2433424974226804,
      "retrieval_config": "qwen_embeddings"
    }
  },
  "reasoning_effort": "none",
  "methodology": {
    "evaluation_date": "2026-05-26",
    "tau2_bench_version": "1.0.1",
    "user_simulator": "gpt-5.2",
    "notes": "Evaluated using GPT-5.2 with reasoning_effort: none. User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking domain evaluated with retrieval_config: qwen_embeddings. banking_knowledge re-graded under tau2-bench v1.0.1 grading fixes on 2026-07-15 (extra-read logging #329, numeric-argument normalization #397, T077-T086 gold trajectories #402); scores prior to v1.0.1 are not comparable.",
    "verification": {
      "modified_prompts": false,
      "omitted_questions": false,
      "details": "Verified evaluation with full trajectory data available. Standard tau-bench scaffold."
    }
  },
  "model_release": {
    "release_date": "2025-12-11",
    "announcement_url": "https://openai.com/index/introducing-gpt-5-2/",
    "announcement_title": "Introducing GPT-5.2"
  }
}