// Evaluate & guard
opencompass0.5.4
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
Open source Maintained For developers
IN ONE PARAGRAPH
opencompass is openCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
Good for: Developers and teams who want to evaluate & guard.
01How to start
- 1Read the official quick-start (link above).
- 2Install from the official package registry:
pip install opencompass - 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → promptfoo Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic. ★ 26k ragas Supercharge Your LLM Application Evaluations 🚀 ★ 16k giskard-oss 🐢 Open-Source Evaluation & Testing library for LLM Agents ★ 5.9k OSWorld [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ★ 3.2k tau2-bench τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains ★ 2.2k
03Related
- ›OpenCompass 文档 · 上海 AI 实验室Chinese & English
- All tutorials →
Versions, why it is listed, for AI to read
Recent releases
- 0.5.4 2026-08-26
- 0.5.3 2026-06-29
- 0.5.2 2026-02-14
- 0.5.1.post1 2025-10-17
- 0.5.1 2025-10-17
For AI agents
- Interfaces：CLI
- Machine-readable record：/api/v1/software/opencompass.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22