{
  "schema_version": "sensebench-run-v2",
  "run_id": "qwen3.8-27b-low-reasoning-p001-lexen-v1-20261013",
  "created_at": "2026-10-13T19:43:36.764900+00:00",
  "git_commit": "56adc7fc800950485db00c464c9b65d18715e975",
  "runner": {
    "github_handle": "emilkayumov",
    "name": "Emil Kaiumov",
    "contact": null
  },
  "dataset": {
    "dataset_id": "lexen",
    "dataset_version": "lexen-v1",
    "dataset_revision": null,
    "content_hash": "sha256:5fd4382b93f19087a1e31f6dd7d1db17c1eb17ff80fcbe1d3fdd55c0c3ecefe8",
    "item_count": 4861
  },
  "prompt": {
    "id": "p001",
    "sensebench_version": "0.1.0"
  },
  "model": {
    "kind": "cloud_llm",
    "display_name": "openrouter/qwen/qwen3.8-27b",
    "requested_model": "openrouter/qwen/qwen3.8-27b",
    "resolved_model": "qwen/qwen3.8-27b",
    "resolved_model_counts": {
      "qwen/qwen3.8-27b": 4868
    },
    "llm_vendor": "Alibaba",
    "api_provider": "OpenRouter",
    "source_kind": "open_source",
    "license": "Apache-2.0",
    "model_url": "https://openrouter.ai/qwen/qwen3.8-27b",
    "reasoning_effort": "low",
    "endpoint_base_url": null
  },
  "fallback_model": null,
  "sampling": {
    "temperature": null,
    "top_p": null,
    "max_tokens": 32768,
    "seed": null,
    "extra": {}
  },
  "policy": {
    "votes_per_item": 1,
    "semantic_reasks_per_invalid_vote": 1,
    "tie_break": "earliest_vote",
    "monosemous_policy": "short_circuit",
    "shuffle_senses_per_vote": false
  },
  "machine": null,
  "execution": {
    "concurrency": 32,
    "warmup_call_count": 0,
    "timing": {
      "benchmark_started_at": "2026-10-13T19:37:20.868183+00:00",
      "benchmark_ended_at": "2026-10-13T19:43:36.763757+00:00",
      "benchmark_seconds": 375.8951765409438,
      "setup_seconds": 1.0401277909986675
    }
  },
  "totals": {
    "item_count": 4861,
    "correct_count": 4452,
    "accuracy": 0.9158609339642049,
    "call_count": 4868,
    "usage": {
      "input_tokens": 3264796,
      "cached_input_tokens": 89536,
      "output_tokens": 1499019,
      "reasoning_output_tokens": 1454465
    },
    "cost": {
      "currency": "USD",
      "total_usd": 3.9927194669,
      "input_uncached_usd": 0.4516185469,
      "input_cached_usd": null,
      "output_usd": 3.54110092,
      "input_uncached_unit_price_usd": null,
      "input_cached_unit_price_usd": null,
      "output_unit_price_usd": null,
      "source": "provider_reported"
    },
    "elapsed_seconds": 375.8951765409438,
    "fallback_used_count": 0
  }
}
