PolyMath-en
Multilingual
text
+
+
+
+
About
PolyMath-EN is the English subset of the PolyMath multilingual mathematical reasoning benchmark, focusing specifically on English-language mathematical problem-solving across multiple difficulty levels. This benchmark provides a standardized evaluation of mathematical reasoning capabilities in English, offering a focused assessment of problem-solving skills, logical reasoning, and mathematical comprehension without cross-lingual complexity.
+
+
+
+
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
65.1%
Average Score
65.1%
High Performers (80%+)
0Top Organizations
#1Moonshot AI
2 models
65.1%
+
+
+
+
Leaderboard
2 models ranked by performance on PolyMath-en
| License | Links | ||||
|---|---|---|---|---|---|
| Jul 11, 2025 | MIT | 65.1% | |||
| Sep 5, 2025 | MIT | 65.1% |
