OmniMath
text
+
+
+
+
About
Omni-MATH is a comprehensive and challenging benchmark specifically designed to assess large language models' mathematical reasoning capabilities at the Olympiad level. It features complex mathematical problems that require advanced reasoning, problem-solving skills, and deep mathematical understanding, providing rigorous evaluation of models' mathematical competency.
+
+
+
+
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
81.9%
Average Score
79.3%
High Performers (80%+)
1Top Organizations
#1Microsoft
2 models
79.3%
+
+
+
+
Leaderboard
2 models ranked by performance on OmniMath
| License | Links | ||||
|---|---|---|---|---|---|
| Apr 30, 2025 | MIT | 81.9% | |||
| Apr 30, 2025 | MIT | 76.6% |
