{"record": {"aliases": [], "artifacts": [], "categories": ["long_context", "reasoning", "structured_output", "tool_calling"], "description": {"en": "ComplexFuncBench is a benchmark designed to evaluate large language models' capabilities in handling complex function calling scenarios. It encompasses multi-step and constrained function calling tasks that require long-parameter filling, parameter value reasoning, and managing contexts up to 128k tokens. The benchmark includes 1,000 samples across five real-world scenarios."}, "documents": [{"document_type": "registry_page", "id": "llm_stats:https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "title": "ComplexFuncBench"}], "evidence_summary": {"document_count": 1, "model_count": 7, "model_count_basis": "source_model_id"}, "key": "llm-stats:complexfuncbench", "modality": "text", "name": "ComplexFuncBench", "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/complexfuncbench?top_n=500"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "llm-stats-complexfuncbench", "source": "llm_stats", "source_benchmark_id": "complexfuncbench"}, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "gpt-4o-2024-08-06", "model_name": "GPT-4o", "obs_id": "llm_stats:complexfuncbench:gpt-4o-2024-08-06", "organization": "OpenAI", "rank_in_source_response": 1, "raw_value": "0.665", "reported_by": "self_reported", "reported_date": "2024-08-06", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.665, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "gpt-4.1-2025-04-14", "model_name": "GPT-4.1", "obs_id": "llm_stats:complexfuncbench:gpt-4.1-2025-04-14", "organization": "OpenAI", "rank_in_source_response": 2, "raw_value": "0.655", "reported_by": "self_reported", "reported_date": "2025-04-14", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.655, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "nova-2-sonic", "model_name": "Nova 2 Sonic", "obs_id": "llm_stats:complexfuncbench:nova-2-sonic", "organization": "Amazon", "rank_in_source_response": 3, "raw_value": "0.652", "reported_by": "self_reported", "reported_date": "2025-12-02", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.652, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "gpt-4.5", "model_name": "GPT-4.5", "obs_id": "llm_stats:complexfuncbench:gpt-4.5", "organization": "OpenAI", "rank_in_source_response": 4, "raw_value": "0.63", "reported_by": "self_reported", "reported_date": "2025-02-27", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.63, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini", "obs_id": "llm_stats:complexfuncbench:gpt-4.1-mini-2025-04-14", "organization": "OpenAI", "rank_in_source_response": 5, "raw_value": "0.493", "reported_by": "self_reported", "reported_date": "2025-04-14", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.493, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "o3-mini", "model_name": "o3-mini", "obs_id": "llm_stats:complexfuncbench:o3-mini", "organization": "OpenAI", "rank_in_source_response": 6, "raw_value": "0.176", "reported_by": "self_reported", "reported_date": "2025-01-30", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.176, "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/complexfuncbench?top_n=500", "key": "llm-stats:complexfuncbench", "measured_by": null, "model_id": "gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano", "obs_id": "llm_stats:complexfuncbench:gpt-4.1-nano-2025-04-14", "organization": "OpenAI", "rank_in_source_response": 7, "raw_value": "0.057", "reported_by": "self_reported", "reported_date": "2025-04-14", "series_id": "llm_stats:complexfuncbench:default", "source": "llm_stats", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500", "value": 0.057, "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:complexfuncbench:gpt-4o-2024-08-06", "reported_at": "2024-08-06", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500"}, "first_score_report": null, "key": "llm-stats:complexfuncbench", "max_score_contradicted": false, "metric": null, "observation_count": 7, "observed_max": 0.665, "score_summary": {"display_max": 66.5, "display_multiplier": 100, "model_count": 7, "model_count_basis": "source_model_id", "numeric_count": 7, "raw_max": 0.665, "raw_min": 0.057, "source_reference": {"crawled_at": "2026-08-17T18:49:35.489925+00:00", "obs_id": "llm_stats:complexfuncbench:gpt-4o-2024-08-06", "reported_date": "2024-08-06", "source_url": "https://api.zeroeval.com/leaderboard/benchmarks/complexfuncbench?top_n=500"}, "unit": null}, "series_id": "llm_stats:complexfuncbench:default"}}}, "siblings": []}
