API-Bank

Multilingual: no

A comprehensive benchmark for tool-augmented LLMs that evaluates API planning, retrieval, and calling capabilities. Contains 314 tool-use dialogues with 753 API calls across 73 API tools, designed to assess how effectively LLMs can utilize external tools and overcome obstacles in tool leveraging.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: reasoning, tool_calling. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 3 of 3 results

Llama 3.1 405B Instruct self-reported llm-stats

92.0%
Llama 3.1 70B Instruct self-reported llm-stats

90.0%
Llama 3.1 8B Instruct self-reported llm-stats

82.6%