Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code on HumanEval (pass@1)
Loading...
67.07
Pass@1
CodePref
51.6052
55.6201
59.635
63.6499
Nov 14, 2025
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
CodePref
Training Method=DPO, D...
2025.11
67.07
UltraMix
Training Method=DPO, D...
2025.11
66.96
UltraMix
Training Method=DPO, D...
2025.11
66.84
UltraMix
Training Method=DPO, D...
2025.11
65.72
TuluDPO
Training Method=DPO, D...
2025.11
65.25
ORPO
Training Method=ORPO,...
2025.11
63.61
HelpSteer
Training Method=DPO, D...
2025.11
60.01
UltraFB
Training Method=DPO, D...
2025.11
57.97
SmolLM-3-3B-SFT
Training Method=SFT
2025.11
52.2
Feedback
Search any
task
Search any
task
