Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Advanced Mathematical Reasoning on AIME Med. + Hard (recovery rate)
Loading...
10.8
Recovery Rate
Bit-Limited Chain-of-Thought (BL-CoT)
6.744
7.797
8.85
9.903
Feb 9, 2026
Recovery Rate
Number of Samples
Updated 13d ago
Evaluation Results
Method
Method
Links
Recovery Rate
Number of Samples
Bit-Limited Chain-of-Thought (BL-CoT)
Protocol=haiku→haiku→h...
2026.02
10.8
34
QA+
Protocol=opus→opus→haiku
2026.02
9.8
34
QA
Protocol=haiku→opus→haiku
2026.02
6.9
34
Feedback
Search any
task
Search any
task