BlogLLM Benchmark Scores as Published, Side by Side
MMLU-ProX: Results as Published
Every result the catalog holds for MMLU-ProX: 26 models from 10 developers, read from 5 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area MultilingualMaintainer Weihao Xuan and co-authors (University of Tokyo and others)Introduced 2025Data version 2026103001, as of 2026-10-30
MMLU-ProX takes the reasoning-focused MMLU-Pro questions and presents the same items in 29 languages. Each language has 11,829 questions in the full set and 658 in the lite set, and each question is multiple choice with 10 options across 57 subjects. Translations were made by language models and then checked by expert review for accurate expression, terminology, and cultural relevance. The paper reports accuracy, including an average across the 29 languages.
MMLU-ProX
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.