Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Coding Reasoning on CodeMMLU
Loading...
82.8
Pass@4
MPD
78.848
79.874
80.9
81.926
May 9, 2026
Pass@4
Token Count
Updated 22d ago
Evaluation Results
Method
Method
Links
Pass@4
Token Count
MPD
2026.05
82.8
2,300
CRISP
2026.05
82.7
4,100
LiteCoT
2026.05
82.1
3,400
Direct Comp.
2026.05
82
2,400
Vanilla LLM
2026.05
81.2
3,600
Chain-of-Draft
2026.05
79
2,000
Feedback
Search any
task
Search any
task