{"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": "Math (math 500)"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "benchmark-saturation:1", "modality": null, "name": "Math (math 500)", "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": "2021-03-05", "released_reference": {"basis": "benchmark_release", "source_key": "benchmark-saturation:1", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "schema_version": 1, "sizes": [], "slug": "benchmark-saturation-1", "source": "benchmark_saturation", "source_benchmark_id": "1", "source_metadata": {"benchmark_saturation": {"dataset_issues": "Contamination, Noisy data, Mislabeling, Other data-related issues", "saturation_index": "0.916397111", "saturation_index_interpreted": "Very high", "test_samples": "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:1", "measured_by": null, "model_id": null, "model_name": "o3", "obs_id": "benchmark_saturation:1:unidentified-8076fca14be660d7265a", "organization": null, "rank_in_source_response": 1, "raw_value": "99.2", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:1:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 99.2, "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:1", "measured_by": null, "model_id": null, "model_name": "Grok-4", "obs_id": "benchmark_saturation:1:unidentified-6d76de8b50dfe64550a6", "organization": null, "rank_in_source_response": 2, "raw_value": "99.0", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:1:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 99.0, "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:1", "measured_by": null, "model_id": null, "model_name": "DeepSeek R1", "obs_id": "benchmark_saturation:1:unidentified-849462e533937d9c7410", "organization": null, "rank_in_source_response": 3, "raw_value": "98.3", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:1:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 98.3, "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:1", "measured_by": null, "model_id": null, "model_name": "GLM-4.5", "obs_id": "benchmark_saturation:1:unidentified-3da864fd83bc80621d41", "organization": null, "rank_in_source_response": 4, "raw_value": "98.2", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:1:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 98.2, "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:1", "measured_by": null, "model_id": null, "model_name": "Claude Opus 4", "obs_id": "benchmark_saturation:1:unidentified-fc77859eb32fab58f39c", "organization": null, "rank_in_source_response": 5, "raw_value": "98.2", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:1:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 98.2, "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:1", "max_score_contradicted": false, "metric": "Accuracy", "observation_count": 5, "observed_max": 99.2, "score_summary": {"display_max": 99.2, "display_multiplier": 1, "model_count": null, "model_count_basis": null, "numeric_count": 5, "raw_max": 99.2, "raw_min": 98.2, "source_reference": {"crawled_at": "2026-11-04T06:47:00Z", "obs_id": "benchmark_saturation:1:unidentified-8076fca14be660d7265a", "reported_date": null, "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "unit": null}, "series_id": "benchmark_saturation:1:default"}}}, "siblings": []}