Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on AIME 2026 (test)
Loading...
14
Baseline Score
ThinkSwitch
9.84
10.92
12
13.08
May 31, 2026
Baseline Score
Best Score
Final Score
Net Gain
Updated 1d ago
Evaluation Results
Method
Method
Links
Baseline Score
Best Score
Final Score
Net Gain
ThinkSwitch
Model Variant=thinking
2026.05
14
22
22
8
ThinkSwitch
Model Variant=instruct
2026.05
10
20
20
10
Feedback
Search any
task
Search any
task
