confident-ai/deepeval
deepeval
The LLM Evaluation Framework
Builder
Confident AI
confident-ai • startup
Stars
14,402
Using upstream star count
Forks
1,318
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Aug 10, 2023
Project creation date
README Summary
DeepEval is a comprehensive LLM evaluation framework that provides unit testing capabilities for LLM outputs with various metrics like hallucination, toxicity, and bias detection. It offers both synthesized and real dataset evaluation with integration support for popular platforms like Pytest, making it easy to incorporate LLM testing into existing workflows. The framework includes confidence scoring and supports custom metrics for thorough evaluation of language model performance.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
production- Quality
- high
- Maturity
- production
Categories
PM Skills
Languages
Timeline
- Project created
- Aug 10, 2023
- Forked
- Nov 8, 2025
- Your last push
- 2 months ago
- Upstream last push
- 8 days ago
- Tracked since
- Feb 6, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…