{
  "schema_version": "sensebench-run-v2",
  "run_id": "gpt-5.5-medium-reasoning-p002-lexen-v1-20260614",
  "created_at": "2026-06-14T02:58:29.150879+00:00",
  "git_commit": "78aebb2a6fd1412a1e8eab85f6209a64f8f441e8",
  "runner": {
    "github_handle": "vassiliphilippov",
    "name": "Vassili Philippov",
    "contact": null
  },
  "dataset": {
    "dataset_id": "lexen",
    "dataset_version": "lexen-v1",
    "dataset_revision": null,
    "content_hash": "sha256:5fd4382b93f19087a1e31f6dd7d1db17c1eb17ff80fcbe1d3fdd55c0c3ecefe8",
    "item_count": 4861
  },
  "prompt": {
    "id": "p002",
    "sensebench_version": "0.1.0"
  },
  "model": {
    "kind": "cloud_llm",
    "display_name": "gpt-5.5",
    "requested_model": "gpt-5.5",
    "resolved_model": "gpt-5.5-2026-04-23",
    "resolved_model_counts": {
      "gpt-5.5-2026-04-23": 4861
    },
    "llm_vendor": "OpenAI",
    "api_provider": "OpenAI",
    "source_kind": "proprietary",
    "license": null,
    "model_url": null,
    "reasoning_effort": "medium",
    "endpoint_base_url": null
  },
  "sampling": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 8192,
    "seed": null,
    "extra": {}
  },
  "policy": {
    "votes_per_item": 1,
    "semantic_reasks_per_invalid_vote": 1,
    "tie_break": "earliest_vote",
    "monosemous_policy": "short_circuit"
  },
  "machine": null,
  "execution": {
    "concurrency": 512,
    "warmup_call_count": 0,
    "timing": {
      "benchmark_started_at": "2026-06-14T02:57:42.468679+00:00",
      "benchmark_ended_at": "2026-06-14T02:58:29.149207+00:00",
      "benchmark_seconds": 46.680270791985095,
      "setup_seconds": 0.9779613749706186
    }
  },
  "totals": {
    "item_count": 4861,
    "correct_count": 4571,
    "accuracy": 0.9403414935198519,
    "call_count": 4861,
    "usage": {
      "input_tokens": 1117887,
      "cached_input_tokens": 0,
      "output_tokens": 427742,
      "reasoning_output_tokens": 379100
    },
    "cost": {
      "currency": "USD",
      "total_usd": 18.421695,
      "input_uncached_usd": 5.589435000000001,
      "input_cached_usd": 0.0,
      "output_usd": 12.83226,
      "input_uncached_unit_price_usd": 5e-6,
      "input_cached_unit_price_usd": 5e-7,
      "output_unit_price_usd": 0.00003,
      "source": "litellm_estimate"
    },
    "elapsed_seconds": 46.680270791985095
  }
}
