reasoning benchmark
ComplexFuncBench
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.
Updated Aug 7, 2026
Published models7
Registry coverage7
MetricScore
EvidenceB
ComplexFuncBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 66.5% | 100.0% | 7 | C | |
| 2 | OP | 65.5% | 83.3% | 7 | C | |
| 3 | AM Nova 2 SonicAmazon | 65.2% | 66.7% | 7 | C | |
| 4 | OP | 63.0% | 50.0% | 7 | C | |
| 5 | OP | 49.3% | 33.3% | 7 | C | |
| 6 | OP | 17.6% | 16.7% | 7 | C | |
| 7 | OP | 5.7% | 0.0% | 7 | C |
Score distribution
Top published rows on the benchmark's original scale.
ComplexFuncBench highlights
The top published results on this benchmark's own scale.
What is ComplexFuncBench?
Definition and scoring fields from the benchmark registry.
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.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- ComplexFuncBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- complexfuncbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about ComplexFuncBench.
Which model scores highest on ComplexFuncBench?
GPT-4o is currently ranked first with 66.5%.
What does ComplexFuncBench measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
7 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.