{"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": "Big Bench Hard (BBH)"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "benchmark-saturation:4", "modality": null, "name": "Big Bench Hard (BBH)", "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": "2022-10-18", "released_reference": {"basis": "benchmark_release", "source_key": "benchmark-saturation:4", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "schema_version": 1, "sizes": [], "slug": "benchmark-saturation-4", "source": "benchmark_saturation", "source_benchmark_id": "4", "source_metadata": {"benchmark_saturation": {"dataset_issues": "Noisy data, Other data-related issues", "saturation_index": "0.2436455949", "saturation_index_interpreted": "Low", "test_samples": "6,511"}}}, "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:4", "measured_by": null, "model_id": null, "model_name": "Claude 3.5 Sonnet", "obs_id": "benchmark_saturation:4:unidentified-6ffcc489a52f9cac8acb", "organization": null, "rank_in_source_response": 1, "raw_value": "93.1", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:4:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 93.1, "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:4", "measured_by": null, "model_id": null, "model_name": "Gemini 1.5 Pro", "obs_id": "benchmark_saturation:4:unidentified-55fcf3adcdf3dc4acdb8", "organization": null, "rank_in_source_response": 2, "raw_value": "89.2", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:4:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 89.2, "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:4", "measured_by": null, "model_id": null, "model_name": "Qwen 3", "obs_id": "benchmark_saturation:4:unidentified-0e9a8d8ca36327fbd137", "organization": null, "rank_in_source_response": 3, "raw_value": "88.87", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:4:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 88.87, "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:4", "measured_by": null, "model_id": null, "model_name": "Kimi K2", "obs_id": "benchmark_saturation:4:unidentified-ba7ef57fdce3f523e61b", "organization": null, "rank_in_source_response": 4, "raw_value": "88.71", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:4:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 88.71, "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:4", "measured_by": null, "model_id": null, "model_name": "Gemma 3 27B", "obs_id": "benchmark_saturation:4:unidentified-de81f9cb471b1510c3c7", "organization": null, "rank_in_source_response": 5, "raw_value": "87.6", "reported_by": "unknown", "reported_date": null, "series_id": "benchmark_saturation:4:default", "source": "benchmark_saturation", "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv", "value": 87.6, "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:4", "max_score_contradicted": false, "metric": "Accuracy", "observation_count": 5, "observed_max": 93.1, "score_summary": {"display_max": 93.1, "display_multiplier": 1, "model_count": null, "model_count_basis": null, "numeric_count": 5, "raw_max": 93.1, "raw_min": 87.6, "source_reference": {"crawled_at": "2026-11-04T06:47:00Z", "obs_id": "benchmark_saturation:4:unidentified-6ffcc489a52f9cac8acb", "reported_date": null, "source_url": "https://github.com/evaleval/benchmark-saturation/blob/6285e3dda145f575a0ccb3f7f4d70cd429832add/data/manual_annotation_data.csv"}, "unit": null}, "series_id": "benchmark_saturation:4:default"}}}, "siblings": []}