Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
ToolBenchgithub.comToolBench is a benchmark for evaluating large language models on software tool manipulation tasks, featuring diverse real-world tools like OpenWeather and Google Sheets. It provides infrastructure to measure execution success rates and supports both OpenAI and HuggingFace models for comparison.
Parse Score
