Wikibench

ComplexFuncBench

reasoning official site →

Multilingual: no

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.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: long_context, reasoning, structured_output, tool_calling. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 7 of 7 results

  1. GPT-4o self-reported llm-stats
    66.5%
  2. GPT-4.1 self-reported llm-stats
    65.5%
  3. Nova 2 Sonic self-reported llm-stats
    65.2%
  4. GPT-4.5 self-reported llm-stats
    63.0%
  5. GPT-4.1 mini self-reported llm-stats
    49.3%
  6. o3-mini self-reported llm-stats
    17.6%
  7. GPT-4.1 nano self-reported llm-stats
    5.7%