{"record": {"aliases": [], "artifacts": [], "categories": ["multimodal", "reasoning", "spatial_reasoning", "vision"], "description": {"en": "TreeBench evaluates visual grounded reasoning, requiring models to localize and reason about fine-grained visual details."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500", "title": "TreeBench"}], "evidence_summary": {"document_count": 1, "model_count": 2, "model_count_basis": "source_model_id"}, "key": "llm-stats:treebench", "modality": "multimodal", "name": "TreeBench", "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/treebench?top_n=500"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "llm-stats-treebench", "source": "llm_stats", "source_benchmark_id": "treebench"}, "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/treebench?top_n=500", "key": "llm-stats:treebench", "measured_by": null, "model_id": "seed-2.1-turbo", "model_name": "Seed 2.1 Turbo", "obs_id": "llm_stats:treebench:seed-2.1-turbo", "organization": "ByteDance", "rank_in_source_response": 1, "raw_value": "0.711", "reported_by": "self_reported", "reported_date": "2026-06-24", "series_id": "llm_stats:treebench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500", "value": 0.711, "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/treebench?top_n=500", "key": "llm-stats:treebench", "measured_by": null, "model_id": "seed-2.1-pro", "model_name": "Seed 2.1 Pro", "obs_id": "llm_stats:treebench:seed-2.1-pro", "organization": "ByteDance", "rank_in_source_response": 2, "raw_value": "0.711", "reported_by": "self_reported", "reported_date": "2026-06-24", "series_id": "llm_stats:treebench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500", "value": 0.711, "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:treebench:seed-2.1-pro", "reported_at": "2026-06-24", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500"}, "first_score_report": null, "key": "llm-stats:treebench", "max_score_contradicted": false, "metric": null, "observation_count": 2, "observed_max": 0.711, "score_summary": {"display_max": 71.1, "display_multiplier": 100, "model_count": 2, "model_count_basis": "source_model_id", "numeric_count": 2, "raw_max": 0.711, "raw_min": 0.711, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:treebench:seed-2.1-pro", "reported_date": "2026-06-24", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/treebench?top_n=500"}, "unit": null}, "series_id": "llm_stats:treebench:default"}}}, "siblings": []}
