reasoning benchmark
ACEBench
ACEBench is a comprehensive benchmark for evaluating Large Language Models' tool usage capabilities across three primary evaluation types: Normal (basic tool usage scenarios), Special (tool usage with ambiguous or incomplete instructions), and Agent (multi-agent interactions simulating real-world dialogues). The benchmark covers 4,538 APIs across 8 major domains and 68 sub-domains including technology, finance, entertainment, society, health, culture, and environment, supporting both English and Chinese languages.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
ACEBench Ranking
Higher score ranks better on this benchmark.
| 01 | MA | 76.5% | 100.0% | 2 | C | |
| 02 | MA | 76.5% | 0.0% | 2 | C |
ACEBench Score Distribution
A closer view of the leading scores on this benchmark.
ACEBench Highlights
The leading models and scores on this benchmark.
What is ACEBench?
What ACEBench measures and how its scores work.
ACEBench is a comprehensive benchmark for evaluating Large Language Models' tool usage capabilities across three primary evaluation types: Normal (basic tool usage scenarios), Special (tool usage with ambiguous or incomplete instructions), and Agent (multi-agent interactions simulating real-world dialogues). The benchmark covers 4,538 APIs across 8 major domains and 68 sub-domains including technology, finance, entertainment, society, health, culture, and environment, supporting both English and Chinese languages.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ACEBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- acebench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ACEBench.
Which model scores highest on ACEBench?
Kimi K2 Instruct is currently ranked first with 76.5%.
What does ACEBench measure?
ACEBench is a comprehensive benchmark for evaluating Large Language Models' tool usage capabilities across three primary evaluation types: Normal (basic tool usage scenarios), Special (tool usage with ambiguous or incomplete instructions), and Agent (multi-agent interactions simulating real-world dialogues). The benchmark covers 4,538 APIs across 8 major domains and 68 sub-domains including technology, finance, entertainment, society, health, culture, and environment, supporting both English and Chinese languages.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.