- Organizations
- University of Edinburgh
University of Edinburgh: AI benchmarks & research
Edinburgh NLP. Maintains MMLU-Redux.
Maintained by University of Edinburgh
2 benchmarks- MMLU-Redux
An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.
- Leader
Qwen3.7 Max95.0%- Models scored
- 50
- MMLU-redux-2.0
A curated version of the MMLU benchmark featuring manually re-annotated 5,700 questions across 57 subjects to identify and correct errors in the original dataset. Addresses the 6.49% error rate found in MMLU and provides more reliable evaluation metrics for language models.
- Leader
Kimi K2 Base90.2%
- Models scored
- 1