Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning and Question Answering on HLE (reference)
Loading...
185
Problems Evaluated
Theoria
175.75
180.375
185
189.625
Jul 1, 2026
Problems Evaluated
Coverage Count
Certified Precision
Wilson 95% CI Lower Bound
Solver Raw Accuracy
Updated 24d ago
Evaluation Results
Method
Method
Links
Problems Evaluated
Coverage Count
Certified Precision
Wilson 95% CI Lower Bound
Solver Raw Accuracy
Theoria
2026.07
185
105
96
84.5
155
Feedback
Search any
task
Search any
task