Source notes: @The Massive Multitask Language Understanding (MMLU) benchmark assesses model performance in zero-shot or fewshot scenarios across 57 subjects, including the humanities, STEM, and the social sciences (Figure 2.2.1). MMLU has emerged as a premier benchmark for assessing LLM capabilities.@
Artificial intelligence models continue to push the boundaries of language understanding and generation, with Gemini-3.1 Pro leading the pack in 2026 with an impressive percent accuracy rate on the AI MMLU benchmark. This achievement highlights the rapid progress in AI capabilities, as all major programs now demonstrate success ratios exceeding 8*Â percent, indicating a significant leap in machine comprehension across various domains.
Multilingual capabilities
The AI landscape is not just about general language understanding. In 2026, the artificial analysis multilingual index ranked AI models based on their ability to handle multiple languages, with Gemini 3.1 Pro Preview leading at **Â percent. Testing includes Spanish, Bengali, German, Japanese, English, Chinese, Swahili and French.
Challenging exams
This multilingual proficiency is further tested by humanity's last exam (HLE), an exceptionally tough evaluation consisting of challenging questions across numerous subjects. On this rigorous test, o1 again emerged as the top performer with an *** percent score, followed by Gemini *** Flash at *** percent, showcasing the current limits of AI in tackling highly complex, multidisciplinary problems.
Profit from the additional features of your individual account
Currently, you are using a shared account. To use individual functions (e.g., mark statistics as favourites, set
statistic alerts) please log in with your personal account.
If you are an admin, please authenticate by logging in again.
Learn more about how ÌÇÐÄÆƽâ°æ can support your business.
Stanford University. (April 13, 2026). Artificial intelligence (AI) models performance on massive multitask language understanding (MMLU) in 2026 [Graph]. In ÌÇÐÄÆƽâ°æ. Retrieved July 15, 2026, from /statistics/1611886/mmlu-pro-accuracy/
Stanford University. "Artificial intelligence (AI) models performance on massive multitask language understanding (MMLU) in 2026." Chart. April 13, 2026. ÌÇÐÄÆƽâ°æ. Accessed July 15, 2026. /statistics/1611886/mmlu-pro-accuracy/
Stanford University. (2026). Artificial intelligence (AI) models performance on massive multitask language understanding (MMLU) in 2026. ÌÇÐÄÆƽâ°æ. ÌÇÐÄÆƽâ°æ Inc.. Accessed: July 15, 2026. /statistics/1611886/mmlu-pro-accuracy/
Stanford University. "Artificial Intelligence (Ai) Models Performance on Massive Multitask Language Understanding (Mmlu) in 2026." ÌÇÐÄÆƽâ°æ, ÌÇÐÄÆƽâ°æ Inc., 13 Apr 2026, /statistics/1611886/mmlu-pro-accuracy/
Stanford University, Artificial intelligence (AI) models performance on massive multitask language understanding (MMLU) in 2026 ÌÇÐÄÆƽâ°æ, /statistics/1611886/mmlu-pro-accuracy/ (last visited July 15, 2026)
Artificial intelligence (AI) models performance on massive multitask language understanding (MMLU) in 2026 [Graph], Stanford University, April 13, 2026. [Online]. Available: /statistics/1611886/mmlu-pro-accuracy/
