{"record": {"aliases": [], "artifacts": [], "categories": ["long_context", "multimodal", "vision"], "description": {"en": "MMLongBench-Doc evaluates long document understanding capabilities in vision-language models."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "title": "MMLongBench-Doc"}], "evidence_summary": {"document_count": 1, "model_count": 5, "model_count_basis": "source_model_id"}, "key": "llm-stats:mmlongbench-doc", "modality": "image", "name": "MMLongBench-Doc", "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/mmlongbench-doc?top_n=500"}, "publisher": null, "released": "2024-07-01", "released_reference": {"basis": "paper_first_version", "note": "First version of the introducing paper: MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations. 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:mmlongbench-doc", "source_url": "https://arxiv.org/abs/2407.01523"}, "schema_version": 1, "sizes": [], "slug": "llm-stats-mmlongbench-doc", "source": "llm_stats", "source_benchmark_id": "mmlongbench-doc"}, "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/mmlongbench-doc?top_n=500", "key": "llm-stats:mmlongbench-doc", "measured_by": null, "model_id": "qwen3.6-plus", "model_name": "Qwen3.6 Plus", "obs_id": "llm_stats:mmlongbench-doc:qwen3.6-plus", "organization": "Qwen", "rank_in_source_response": 1, "raw_value": "0.62", "reported_by": "self_reported", "reported_date": "2026-04-02", "series_id": "llm_stats:mmlongbench-doc:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "value": 0.62, "value_kind": "number"}, {"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/mmlongbench-doc?top_n=500", "key": "llm-stats:mmlongbench-doc", "measured_by": null, "model_id": "qwen3.5-27b", "model_name": "Qwen3.5-27B", "obs_id": "llm_stats:mmlongbench-doc:qwen3.5-27b", "organization": "Qwen", "rank_in_source_response": 2, "raw_value": "0.602", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:mmlongbench-doc:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "value": 0.602, "value_kind": "number"}, {"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/mmlongbench-doc?top_n=500", "key": "llm-stats:mmlongbench-doc", "measured_by": null, "model_id": "qwen3.5-35b-a3b", "model_name": "Qwen3.5-35B-A3B", "obs_id": "llm_stats:mmlongbench-doc:qwen3.5-35b-a3b", "organization": "Qwen", "rank_in_source_response": 3, "raw_value": "0.595", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:mmlongbench-doc:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "value": 0.595, "value_kind": "number"}, {"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/mmlongbench-doc?top_n=500", "key": "llm-stats:mmlongbench-doc", "measured_by": null, "model_id": "qwen3.5-122b-a10b", "model_name": "Qwen3.5-122B-A10B", "obs_id": "llm_stats:mmlongbench-doc:qwen3.5-122b-a10b", "organization": "Qwen", "rank_in_source_response": 4, "raw_value": "0.59", "reported_by": "self_reported", "reported_date": "2026-02-24", "series_id": "llm_stats:mmlongbench-doc:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "value": 0.59, "value_kind": "number"}, {"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/mmlongbench-doc?top_n=500", "key": "llm-stats:mmlongbench-doc", "measured_by": null, "model_id": "qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 VL 235B A22B Thinking", "obs_id": "llm_stats:mmlongbench-doc:qwen3-vl-235b-a22b-thinking", "organization": "Qwen", "rank_in_source_response": 5, "raw_value": "0.562", "reported_by": "self_reported", "reported_date": "2025-09-22", "series_id": "llm_stats:mmlongbench-doc:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500", "value": 0.562, "value_kind": "number"}], "series": {"bounds": {"basis": "aggregator_declared", "max": 100.0, "min": null}, "declared_max": 100.0, "direction": "higher_is_better", "direction_basis": "source_rank_descending", "display_scale": null, "first_score_record": {"date_precision": "model_announcement", "obs_id": "llm_stats:mmlongbench-doc:qwen3-vl-235b-a22b-thinking", "reported_at": "2025-09-22", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500"}, "first_score_report": null, "key": "llm-stats:mmlongbench-doc", "max_score_contradicted": false, "metric": null, "observation_count": 5, "observed_max": 0.62, "score_summary": {"display_max": 0.62, "display_multiplier": 1, "model_count": 5, "model_count_basis": "source_model_id", "numeric_count": 5, "raw_max": 0.62, "raw_min": 0.562, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:mmlongbench-doc:qwen3.6-plus", "reported_date": "2026-04-02", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/mmlongbench-doc?top_n=500"}, "unit": null}, "series_id": "llm_stats:mmlongbench-doc:default"}}}, "siblings": []}
