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.
Kimi K2 Instruct from Moonshot AI currently leads the ACEBench leaderboard with a score of 0.765 across 2 evaluated AI models.
What ACEBench measures
ACEBench is a text benchmark that evaluates large language models on finance, general, healthcare, reasoning, and tool calling tasks. LLM Stats tracks 2 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 0.8.
Compare leaders on the best AI for finance, best AI for general, best AI for healthcare, best AI for reasoning and best AI for tool calling leaderboards.
Publication
- Paper
- ACEBench: Who Wins the Match Point in Tool Usage?
- Authors
- Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, and 12 others
- Published
- arXiv
- 2501.12851
Abstract
Large Language Models (LLMs) have demonstrated significant potential in decision-making and reasoning, particularly when integrated with various tools to effectively solve complex problems. However, existing benchmarks for evaluating LLMs' tool usage face several limitations: (1) limited evaluation scenarios, often lacking assessments in real multi-turn dialogue contexts; (2) narrow evaluation dimensions, with insufficient detailed assessments of how LLMs use tools; and (3) reliance on LLMs or real API executions for evaluation, which introduces significant overhead. To address these challenges, we introduce ACEBench, a comprehensive benchmark for assessing tool usage in LLMs. ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. "Normal" evaluates tool usage in basic scenarios; "Special" evaluates tool usage in situations with ambiguous or incomplete instructions; "Agent" evaluates tool usage through multi-agent interactions to simulate real-world, multi-turn dialogues. We conducted extensive experiments using ACEBench, analyzing various LLMs in-depth and providing a more granular examination of error causes across different data types.
Kimi K2 Instruct leads with 76.5%, followed by Kimi K2-Instruct-0905 at 76.5%.
Progress Over Time
Interactive timeline showing model performance evolution on ACEBench
ACEBench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Moonshot AI | 1.0T | — | — | ||
| 1 | Moonshot AI | 1.0T | — | — |
FAQ
Common questions about ACEBench.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions