Popular repositories Loading

1. LLMEval-1 LLMEval-1 Public

   [AAAI 2024] LLMEval Phase I dataset — 17 categories, 453 questions, 2186 annotators for Chinese LLM evaluation

   114 2

2. LLMEval-2 LLMEval-2 Public

   [AAAI 2024] LLMEval Phase II dataset — professional domain evaluation across 12 academic disciplines

   71 4

3. LLMEval-Fair LLMEval-Fair Public

   [ACL 2026] A large-scale longitudinal study on robust and fair evaluation of LLMs — 200K+ generative questions across 13 disciplines

   37 2

4. LLMEval-Med LLMEval-Med Public

   [EMNLP 2025] A real-world clinical benchmark for medical LLMs with physician validation — 2,996 questions from EHRs

   Python 27 1

5. Llmeval-Gaokao2024-Math Llmeval-Gaokao2024-Math Public

   LLM evaluation on 2024 Chinese Gaokao Mathematics — zero-contamination benchmark with dual prompt formats

   19 1

6. LLMEval-Logic LLMEval-Logic Public

   LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening (80% public release; 20% private holdout)

   Python 9