{"record": {"aliases": [], "artifacts": [], "categories": ["healthcare", "vision"], "description": {"en": "CheXpert is a large dataset of 224,316 chest radiographs from 65,240 patients for automated chest X-ray interpretation. The dataset includes uncertainty labels for 14 medical observations extracted from radiology reports. It serves as a benchmark for developing and evaluating automated chest radiograph interpretation models."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500", "title": "CheXpert CXR"}], "evidence_summary": {"document_count": 1, "model_count": 1, "model_count_basis": "source_model_id"}, "key": "llm-stats:chexpert-cxr", "modality": "image", "name": "CheXpert CXR", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"crawl_bundle": "llm_stats_2026-08-17", "crawled_at": "2026-08-17T18:49:35.489925+00:00", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500"}, "publisher": null, "released": "2019-01-21", "released_reference": {"basis": "paper_first_version", "note": "First version of the introducing paper: CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. The source-record description identifies this benchmark or its original partition; no dates or scores are joined by name at runtime.", "source_key": "llm-stats:chexpert-cxr", "source_url": "https://arxiv.org/abs/1901.07031"}, "schema_version": 1, "sizes": [], "slug": "llm-stats-chexpert-cxr", "source": "llm_stats", "source_benchmark_id": "chexpert-cxr"}, "schema_version": 1, "scores_by_source": {"llm_stats": {"rows": [{"comparable_group": null, "crawled_at": "2026-08-17T18:49:35.489925+00:00", "date_precision": "model_announcement", "document_id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500", "key": "llm-stats:chexpert-cxr", "measured_by": null, "model_id": "medgemma-4b-it", "model_name": "MedGemma 4B IT", "obs_id": "llm_stats:chexpert-cxr:medgemma-4b-it", "organization": "Google", "rank_in_source_response": 1, "raw_value": "0.481", "reported_by": "self_reported", "reported_date": "2025-05-20", "series_id": "llm_stats:chexpert-cxr:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500", "value": 0.481, "value_kind": "number"}], "series": {"bounds": {"basis": "aggregator_declared", "max": 1.0, "min": null}, "declared_max": 1.0, "direction": "higher_is_better", "direction_basis": "source_rank_descending", "display_scale": null, "first_score_record": {"date_precision": "model_announcement", "obs_id": "llm_stats:chexpert-cxr:medgemma-4b-it", "reported_at": "2025-05-20", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500"}, "first_score_report": null, "key": "llm-stats:chexpert-cxr", "max_score_contradicted": false, "metric": null, "observation_count": 1, "observed_max": 0.481, "score_summary": {"display_max": 48.1, "display_multiplier": 100, "model_count": 1, "model_count_basis": "source_model_id", "numeric_count": 1, "raw_max": 0.481, "raw_min": 0.481, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:chexpert-cxr:medgemma-4b-it", "reported_date": "2025-05-20", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/chexpert-cxr?top_n=500"}, "unit": null}, "series_id": "llm_stats:chexpert-cxr:default"}}}, "siblings": []}
