reasoning benchmark
ACEBench Leaderboard
ACEBench evaluates Large Language Models' tool usage capabilities across Normal, Special, and Agent evaluation types, covering 4,538 APIs in 8 major domains and 68 sub-domains in English and Chinese.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
ACEBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score76.50% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score76.50% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
ACEBench Highlights
The leading models and scores on this benchmark.
ACEBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for ACEBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is ACEBench?
What ACEBench measures and how its scores work.
ACEBench is a benchmark for evaluating Large Language Models' tool usage across basic tool usage scenarios, ambiguous or incomplete instructions, and multi-agent interactions simulating real-world dialogues.
It measures tool usage capabilities with a Score reported as a ratio across 4,538 APIs in 8 major domains and 68 sub-domains, supporting English and Chinese.
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
- overall
LLM Stats. 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 76.50%.
What are the top three models on ACEBench?
The current leaders are Kimi K2 Instruct (76.50%) and Kimi K2-Instruct-0905 (76.50%).
Which ACEBench model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among ACEBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.