{"record": {"aliases": [], "artifacts": [], "categories": [], "description": {}, "documents": [{"document_type": "registry_page", "id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "title": "HEAD-QA: A Healthcare Dataset for Complex Reasoning"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "benchmark-saturation:29", "modality": null, "name": "HEAD-QA: A Healthcare Dataset for Complex Reasoning", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"crawl_bundle": "benchmark_saturation_2026-11-04", "crawled_at": "2026-11-04T06:47:00Z", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "publisher": null, "released": "2019-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "benchmark-saturation:29", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "schema_version": 1, "sizes": [], "slug": "benchmark-saturation-29", "source": "benchmark_saturation", "source_benchmark_id": "29", "source_metadata": {"benchmark_saturation": {"dataset_issues": "Noisy data", "saturation_index": "0.7493811906", "saturation_index_interpreted": "High", "test_samples": "2,742"}}}, "schema_version": 1, "scores_by_source": {"benchmark_saturation": {"rows": [{"comparable_group": null, "crawled_at": "2026-11-04T06:47:00Z", "date_precision": "model_announcement", "document_id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "key": "benchmark-saturation:29", "measured_by": null, "model_id": null, "model_name": "Claude 3.7 Sonnet (20250219)", "obs_id": "benchmark_saturation:29:unidentified-e15e5b5b824446831378", "organization": null, "rank_in_source_response": 1, "raw_value": "91.2", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:29:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 91.2, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-11-04T06:47:00Z", "date_precision": "model_announcement", "document_id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "key": "benchmark-saturation:29", "measured_by": null, "model_id": null, "model_name": "Claude 3.5 Sonnet (20241022)", "obs_id": "benchmark_saturation:29:unidentified-0d6d611e217e1483405c", "organization": null, "rank_in_source_response": 2, "raw_value": "90.6", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:29:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 90.6, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-11-04T06:47:00Z", "date_precision": "model_announcement", "document_id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "key": "benchmark-saturation:29", "measured_by": null, "model_id": null, "model_name": "GPT-4o (2024-05-13)", "obs_id": "benchmark_saturation:29:unidentified-a684601c9734442b5c1f", "organization": null, "rank_in_source_response": 3, "raw_value": "90.6", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:29:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 90.6, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-11-04T06:47:00Z", "date_precision": "model_announcement", "document_id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "key": "benchmark-saturation:29", "measured_by": null, "model_id": null, "model_name": "o3-mini (2025-01-31)", "obs_id": "benchmark_saturation:29:unidentified-a82d40950ee1711b58b4", "organization": null, "rank_in_source_response": 4, "raw_value": "89.3", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:29:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 89.3, "value_kind": "number"}, {"comparable_group": null, "crawled_at": "2026-11-04T06:47:00Z", "date_precision": "model_announcement", "document_id": "benchmark_saturation:https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "key": "benchmark-saturation:29", "measured_by": null, "model_id": null, "model_name": "Gemini 2.0 Flash", "obs_id": "benchmark_saturation:29:unidentified-b9ace5730fd5e4384a1e", "organization": null, "rank_in_source_response": 5, "raw_value": "88", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:29:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 88.0, "value_kind": "number"}], "series": {"bounds": {"basis": "aggregator_declared", "max": null, "min": null}, "declared_max": null, "direction": "higher_is_better", "direction_basis": "source_rank_descending", "display_scale": null, "first_score_record": null, "first_score_report": null, "key": "benchmark-saturation:29", "max_score_contradicted": false, "metric": "Accuracy", "observation_count": 5, "observed_max": 91.2, "score_summary": {"display_max": 91.2, "display_multiplier": 1, "model_count": null, "model_count_basis": null, "numeric_count": 5, "raw_max": 91.2, "raw_min": 88.0, "source_reference": {"crawled_at": "2026-11-04T06:47:00Z", "obs_id": "benchmark_saturation:29:unidentified-e15e5b5b824446831378", "reported_date": null, "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "unit": null}, "series_id": "benchmark_saturation:29:default"}}}, "siblings": []}