8 Best Hallucination Leaderboard Alternatives in 2026 (Open Source)
Hallucination Leaderboard — Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents. The only continuously-updated automated hallucination benchmark using a dedicated evaluation model (HHEM) rather than human annotations, enabling scalable and repeatable factual consistency measurement across 7,700+ test documents
These 8 open-source tools do the same job. They are ordered by how closely they match Hallucination Leaderboard, with live GitHub data so you can see which projects are actively maintained.
| Tool | GitHub stars | Stars / 30d | Last commit |
|---|---|---|---|
| Hallucination Leaderboard(original) | 3.3k | +25 | 2026-09-23 |
| DeepEval | 18.5k | +676 | 2026-09-29 |
| Ragas | 15.9k | +443 | 2026-02-24 |
| Auto-evaluator | 1.1k | +52 | 2023-05-10 |
| UQLM | 1.2k | +12 | 2026-09-03 |
| OpenAI Evals | 19.5k | +231 | 2026-04-14 |
| LLM-eval-survey | 1.6k | +3 | 2026-09-13 |
| UpTrain | 2.4k | +4 | 2024-07-29 |
| LLM Comparator | 526 | +1 | 2024-10-18 |
1. DeepEval
The LLM Evaluation Framework
What sets it apart: Most comprehensive open-source LLM eval framework with 30+ research-backed metrics including agentic, RAG, multi-turn, MCP, and multimodal — vs Ragas (RAG-only) or custom eval scripts
Best for: Teams needing comprehensive LLM/agent evaluation pipelines; CI/CD integration for LLM app quality gates; RAG pipeline evaluation and optimization
2. Ragas
Supercharge Your LLM Application Evaluations 🚀
What sets it apart: vs manual LLM evaluation: Purpose-built evaluation framework with both LLM-based and traditional metrics, automated test generation, and seamless integration with popular LLM frameworks
Best for: Evaluating RAG pipeline quality with automated metrics; Generating comprehensive test datasets for LLM apps; Building continuous evaluation feedback loops
3. Auto-evaluator
Evaluation tool for LLM QA chains
What sets it apart: Lightweight QA evaluation tool that auto-generates question-answer pairs from documents and scores LLM chain configurations
Best for: evaluating-qa-chain-configurations; comparing-retrieval-strategies; rapid-llm-evaluation-prototyping
4. UQLM
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
What sets it apart: Academically rigorous uncertainty quantification (published in JMLR/TMLR) with the broadest scorer variety — unlike guardrails tools that use simple heuristics, UQLM applies information-theoretic methods like semantic entropy for precise hallucination detection
Best for: Adding hallucination detection to existing LLM applications; Research teams studying LLM uncertainty and reliability
5. OpenAI Evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Best for: Teams systematically evaluating LLM performance across model versions; Prompt engineers needing no-code YAML-based evaluation workflows; Organizations building quality assurance pipelines for LLM applications
6. LLM-eval-survey
The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".
What sets it apart: Comprehensive survey and curated collection of LLM evaluation papers and resources organized by what, where, and how to evaluate
Best for: llm-evaluation-research; finding-evaluation-benchmarks; understanding-eval-landscape
7. UpTrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform ro
What sets it apart: vs generic eval tools: 20+ preconfigured evaluations with customizable prompts, few-shot examples, and scenario descriptions — all running locally for data privacy with root cause analysis on failures
Best for: RAG system evaluation and quality assurance; LLM application testing before production deployment; Safety and security testing for prompt injection vulnerabilities
8. LLM Comparator
LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.
What sets it apart: vs generic eval dashboards: combines visual analytics with rationale clustering and custom field analysis to identify specific behavioral differences between models — from Google PAIR team
Best for: Comparing two LLM outputs with numerical evaluation scores; Discovering when and why one model outperforms another; Analyzing response patterns across prompt categories