Inference
MMLU-ProX authors

MMLU-ProX

A multilingual extension of professional-level academic evaluation across many languages.

ModelsModels with a result.12
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.2025

Result and price

020406080100$1$3$10$30RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

12 results
#ModelResultThe score from the source.
—Qwen3.7 Max87.0%
—Claude Opus 4.585.7%
—Qwen3.7 Plus85.4%
—Qwen3.6 Plus84.7%
—Qwen3.5 397B84.7%
—GLM-583.1%
—Nemotron 3 Ultra83.0%
—Kimi K2.582.3%
—Qwen3.5-122B-A10B82.2%
—Qwen3.5-27B82.2%
—Qwen3.5-35B-A3B81.0%
—Qwen3 235B 250779.4%