whereismyai
OpenCompass
OpenCompass is an open-source LLM evaluation platform that provides benchmarks, leaderboards, and evaluation tools for AI models.
OpenCompass builds a standardized metric system for the artificial intelligence era, providing objective and traceable evaluation leaderboards. It evaluates large language models, multimodal models, and scientific AI models across dimensions such as language, reasoning, knowledge, mathematics, coding, instruction following, and agents. The platform serves AI enthusiasts, application developers, model manufacturers, and academic institutions. Users can browse evaluation leaderboards, test sets, and developer documentation, as well as participate in model arena voting. It features regular updates and tracks frontier models from various developers.
OpenCompass at a glance
- Best for: Software engineer, Researcher
- Runs on: open source, Web
- Pricing: Free
- Released: June 2023
- Category: AI research tool
- Website: opencompass.org.cn
Key features
- Large language model evaluation
- Multimodal model evaluation
- Scientific AI model evaluation
- Evaluation leaderboards
- Model arena voting
- Evaluation datasets
- Evaluation tools
Use it for
- Track frontier AI models
- Browse objective evaluation leaderboards
- Participate in model arena voting
- Evaluate large language and multimodal models
Alternatives to OpenCompass
- OpenResearch — Run parallel research workflows locally or on remote compute.
- OpenVLHarness — Lifts six multimodal model backbones by 9.7 to 12.6 points across 22 benchmarks.
- LM Arena — Compare anonymous AI models blindly and vote on the best outputs.
- OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
- OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
- LLM Stats — Independent rankings updated continuously from live API metrics.
- LMMs-Eval — Provides open research and tooling for multimodal model evaluation and benchmarks.
- OpenSquilla — Maximizes AI intelligence density while minimizing token costs through smart routing.
- OpenLIT — It enables comprehensive monitoring, evaluation, and management of AI agents via OpenTelemetry.
- MLflow — Complete observability and evaluation for production AI apps.
- OpenLLM — It simplifies infrastructure management and optimizes inference speed and cost.
- Opik — It offers comprehensive tracing, automated evaluations, and open-source flexibility.
All OpenCompass alternatives