Benchmark
ComplexFuncBench
What is ComplexFuncBench?
ComplexFuncBench is a benchmark designed to evaluate large language models' capabilities in handling complex function calling scenarios. It encompasses…
- Modality
- text
- Evaluates
- long context, reasoning, structured output, tool calling
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 7
Source provenance
ComplexFuncBench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.655 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.493 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.057 | 2025-04-14 | evidence |
| GPT-4.5 | OpenAI | 0.63 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.665 | 2024-08-06 | evidence |
| Nova 2 Sonic | Amazon | 0.652 | 2025-12-02 | evidence |
| o3-mini | OpenAI | 0.176 | 2025-01-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.