Hallucination Leaderboard vs LLM-eval-survey

Side-by-side comparison of two AI agent tools

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

Metrics

Hallucination LeaderboardLLM-eval-survey
Stars3.3k1.6k
Star velocity /mo25.026737967914443.0481283422459895
Commits (90d)27
Releases (6m)00
Overall score0.52357865139641240.44606203485415574

Pros

  • +Regularly updated with latest model versions and performance data, ensuring current relevance for model selection decisions
  • +Uses standardized HHEM evaluation methodology providing consistent and comparable metrics across all tested models
  • +Comprehensive metrics beyond just hallucination rates including factual consistency, answer rates, and summary length statistics
  • +Comprehensive coverage of LLM evaluation across diverse domains including NLP, ethics, science, and medical applications
  • +Backed by authoritative survey paper from leading academic institutions and Microsoft Research
  • +Actively maintained with community contributions and real-time updates beyond the original arXiv publication

Cons

  • -Limited to summarization tasks only, not covering other common LLM use cases like code generation or creative writing
  • -No API access mentioned for programmatic integration into model selection workflows
  • -Primarily academic resource focused on papers and methodologies rather than ready-to-use evaluation tools
  • -May require significant domain expertise to effectively implement the suggested evaluation frameworks
  • -Limited practical implementation guidance for organizations without strong research backgrounds

Use Cases

  • •Selecting the most reliable LLM for production summarization applications where factual accuracy is critical
  • •Academic research into hallucination patterns and model reliability across different architectures and training approaches
  • •Benchmarking new models against established baselines to evaluate improvements in factual consistency
  • •Academic researchers developing new LLM evaluation methodologies or benchmarking existing approaches
  • •AI practitioners seeking comprehensive evaluation frameworks to assess model performance across multiple dimensions
  • •Organizations implementing responsible AI practices who need systematic approaches to evaluate model robustness, bias, and trustworthiness