> ## Documentation Index > Fetch the complete documentation index at: https://openbench.dev/llms.txt > Use this file to discover all available pages before exploring further. # Reasoning > Evaluate AI models on reasoning, logic, and multimodal understanding openbench provides comprehensive reasoning benchmarks covering factuality, logical reasoning, multi-hop inference, and multimodal understanding across diverse domains. ## Available Benchmarks Tests factuality and accuracy on straightforward questions with verifiable answers. ```bash theme={null} bench eval simpleqa ``` Multi-Step Reasoning benchmark with murder mysteries, object placements, and team allocation problems. ```bash theme={null} bench eval musr ``` Discrete Reasoning Over Paragraphs - numerical and span-based reasoning over text. ```bash theme={null} bench eval drop ``` Multi-hop reasoning through graph structures to test navigation and inference. ```bash theme={null} bench eval graphwalks ``` Web browsing agent tasks requiring navigation and information synthesis. ```bash theme={null} bench eval browsecomp ``` Massive Multi-discipline Multimodal Understanding across college-level subjects. ```bash theme={null} bench eval mmmu ``` Enhanced version of MMMU with more challenging multimodal problems. ```bash theme={null} bench eval mmmu_pro ``` ## Related Resources * [SimpleQA by OpenAI](https://openai.com/index/introducing-simpleqa/) * [MuSR Paper](https://arxiv.org/abs/2310.16049) * [DROP Paper](https://arxiv.org/abs/1903.00161) * [MMMU Paper](https://arxiv.org/abs/2311.16502)