Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Complex Reasoning on MMLU-Pro (test)
Loading...
28.6
Accuracy
Naïve Summary
9.776
14.663
19.55
24.437
Jul 2, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Naïve Summary
Avg KV Cache=277.4, Av...
2026.07
28.6
No Repetition
Avg KV Cache=235.5, Av...
2026.07
27.8
PARTREP
Avg KV Cache=280.4, Av...
2026.07
27.8
LLMLingua
Avg KV Cache=277.4, Av...
2026.07
27.7
H2O Eviction
Avg KV Cache=270.8, Av...
2026.07
27.4
Full Repetition
Avg KV Cache=471.1, Av...
2026.07
27.3
Echo Eviction
Avg KV Cache=235.5, Av...
2026.07
22
LLMLingua Comp.
Avg KV Cache=78.6, Avg...
2026.07
10.5
Feedback
Search any
task
Search any
task