InterGPS
text
+
+
+
+
About
InterGPS (Interpretable Geometry Problem Solving) is a geometry reasoning benchmark that evaluates AI models' ability to solve geometric problems using formal language and symbolic reasoning. This benchmark tests models' mathematical reasoning capabilities through geometry problems requiring spatial understanding, theorem application, and step-by-step logical deduction with interpretable solution paths.
+
+
+
+
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
48.6%
Average Score
42.4%
High Performers (80%+)
0Top Organizations
#1Microsoft
2 models
42.4%
+
+
+
+
Leaderboard
2 models ranked by performance on InterGPS
| License | Links | ||||
|---|---|---|---|---|---|
| Feb 1, 2025 | MIT | 48.6% | |||
| Aug 23, 2024 | MIT | 36.3% |
