Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GeoTrust

Benchmarks

Task NameDataset NameSOTA ResultTrend
Geometric Problem SolvingGeoTrust (test)
Accuracy45.83
15
Geometric Problem SolvingGeoTrust Tier4 (test)
Count23
9
Geometric Problem SolvingGeoTrust Tier3 (test)
Count26
9
Geometric Problem SolvingGeoTrust Tier2 (test)
Count24
9
Geometric Problem SolvingGeoTrust Tier1 (test)
Count37
9
Showing 5 of 5 rows