GenExam
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GenExam-Math (test)
8Structural Correctness
20
GenExam Math (Overall)
68.2Strict Accuracy
14
GenExam Relaxed Score
87.8Math Score (GenExam Relaxed)
13
GenExam
86.3Math Score
13
GenExam
52.3Math-Rel Score
7
GenExam
93.8Performance Score
5
GenExam math
68.2Strict Accuracy
3
GenExam
80ISVGEN
3
GenExam Math Plane + Analytic (2D)
72.1Strict Accuracy
1
GenExam Math Solid Geometry (3D)
18.2Strict Accuracy
1
GenExam Math Analytic Geometry
80.4Strict Accuracy
1
GenExam Math (Plane Geometry)
66.7Strict Accuracy
1