Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Reasoning (Input Prediction) on CruxEval-I
Loading...
35.7
CX-I
50% CodeEnhance + 50% Nemotron-RW
29.252
30.926
32.6
34.274
Jun 8, 2026
CX-I
Updated 1mo ago
Evaluation Results
Method
Method
Links
CX-I
50% CodeEnhance + 50% Nemotron-RW
Tokens (B)=10
2026.06
35.7
CodeEnhance
Tokens (B)=10
2026.06
35.3
CodeEnhance+Nemotron-RW+SwallowCode
Tokens (B)=10
2026.06
34.6
90% CodeEnhance+CodeQA + 10% Raw
Tokens (B)=10
2026.06
34.5
CodeEnhance-gemma-4b
Tokens (B)=10
2026.06
33.8
CodeEnhance+CodeQA
Tokens (B)=10
2026.06
33.6
95% CodeEnhance+CodeQA + 5% Raw
Tokens (B)=10
2026.06
33.6
Nemotron-RW
Tokens (B)=10
2026.06
32.3
SwallowCode
Tokens (B)=10
2026.06
31.2
CodeEnhance-gemma-1b
Tokens (B)=10
2026.06
29.5
Feedback
Search any
task
Search any
task