FunctionalMATH
text
+
+
+
+
About
FunctionalMATH is a mathematical reasoning benchmark that uses functional variants to provide robust evaluation of language models' mathematical capabilities. This benchmark focuses on mathematical problem-solving through functional programming approaches, testing models' ability to apply mathematical reasoning in computational contexts and evaluate mathematical functions accurately across diverse problem domains.
+
+
+
+
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
64.6%
Average Score
59.1%
High Performers (80%+)
0Top Organizations
#1Google
2 models
59.1%
+
+
+
+
Leaderboard
2 models ranked by performance on FunctionalMATH
| License | Links | ||||
|---|---|---|---|---|---|
| May 1, 2024 | Proprietary | 64.6% | |||
| May 1, 2024 | Proprietary | 53.6% |
