{"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": "Humanity’s Last Exam"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "benchmark-saturation:53", "modality": null, "name": "Humanity’s Last Exam", "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": "2025-01-27", "released_reference": {"basis": "benchmark_release", "source_key": "benchmark-saturation:53", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "schema_version": 1, "sizes": [], "slug": "benchmark-saturation-53", "source": "benchmark_saturation", "source_benchmark_id": "53", "source_metadata": {"benchmark_saturation": {"dataset_issues": "Contamination", "saturation_index": "0.219757739", "saturation_index_interpreted": "Low", "test_samples": "2,500"}}}, "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:53", "measured_by": null, "model_id": null, "model_name": "Gemini 3 pro preview", "obs_id": "benchmark_saturation:53:unidentified-a915dac8be9c17288d42", "organization": null, "rank_in_source_response": 1, "raw_value": "37.72", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:53:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 37.72, "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:53", "measured_by": null, "model_id": null, "model_name": "gpt-5-pro-2025-10-06", "obs_id": "benchmark_saturation:53:unidentified-8493cd68eae9f7214768", "organization": null, "rank_in_source_response": 2, "raw_value": "33.32", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:53:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 33.32, "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:53", "measured_by": null, "model_id": null, "model_name": "gpt-5.2-2025-12-11", "obs_id": "benchmark_saturation:53:unidentified-c40fc94eb0cae206590d", "organization": null, "rank_in_source_response": 3, "raw_value": "28.50", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:53:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 28.5, "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:53", "measured_by": null, "model_id": null, "model_name": "gpt-5-2025-08-07", "obs_id": "benchmark_saturation:53:unidentified-11c45dae5f48e6aba800", "organization": null, "rank_in_source_response": 4, "raw_value": "26.32", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:53:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 26.32, "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:53", "measured_by": null, "model_id": null, "model_name": "claude-opus-4-5-20251101-thinking", "obs_id": "benchmark_saturation:53:unidentified-467bc7220416f02851bb", "organization": null, "rank_in_source_response": 5, "raw_value": "26.32", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:53:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 26.32, "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:53", "max_score_contradicted": false, "metric": "LLM-as-a-Judge", "observation_count": 5, "observed_max": 37.72, "score_summary": {"display_max": 37.72, "display_multiplier": 1, "model_count": null, "model_count_basis": null, "numeric_count": 5, "raw_max": 37.72, "raw_min": 26.32, "source_reference": {"crawled_at": "2026-11-04T06:47:00Z", "obs_id": "benchmark_saturation:53:unidentified-a915dac8be9c17288d42", "reported_date": null, "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "unit": null}, "series_id": "benchmark_saturation:53:default"}}}, "siblings": []}