Share your thoughts, 1 month free Claude Pro on usSee more

Code Generation on HumanEval+ (Accuracy, Follow Rate)

77.44Accuracy

Qwen-2.5-7B-Instruct

Updated 1mo ago

Evaluation Results

Method	Links
Qwen-2.5-7B-Instruct 2026.06		77.44	-
Qwen-2.5-7B-Instruct 2026.06		76.22	-
A.X-4.0-Light 2026.06		75	-
EXAONE-3.5-7.8B-Instruct 2026.06		75	-
Kanana-1.5-8B-Instruct 2026.06		75	-
A.X-4.0-Light 2026.06		75	-
Kanana-1.5-8B-Instruct 2026.06		75	-
EXAONE-3.5-7.8B-Instruct 2026.06		73.78	-
Gemma-3-4B-IT 2026.06		61.59	-
Gemma-3-4B-IT 2026.06		61.59	-
Llama-3.1-8B-Instruct 2026.06		59.15	-
Llama-3.1-8B-Instruct 2026.06		58.54	-