OpenAI MMLU
text
+
+
+
+
About
OpenAI MMLU is OpenAI's implementation of the Massive Multitask Language Understanding benchmark, evaluating AI models across 57 academic subjects from elementary to professional levels. This comprehensive assessment tests knowledge spanning humanities, STEM, social sciences, and professional domains, serving as a standardized measure of general intelligence and academic competency in language models.
+
+
+
+
Evaluation Stats
Total Models2
Organizations1
Verified Results0
Self-Reported2
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
2 models
Top Score
35.6%
Average Score
28.9%
High Performers (80%+)
0Top Organizations
#1Google
2 models
28.9%
+
+
+
+
Leaderboard
2 models ranked by performance on OpenAI MMLU
| License | Links | ||||
|---|---|---|---|---|---|
| Jun 26, 2025 | Proprietary | 35.6% | |||
| Jun 26, 2025 | Proprietary | 22.3% |
