Big Code Memorization: leaderboard

Code-generation evaluation from the Memorization or Generation of Big Code Models study, comparing HumanEval solutions with transformed HumanEval-ET variants that stress generalization.

Metric: HumanEval pass@1 (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1deepseek-coder-6.7B-instruct71.34
2GPT-3.5 Turbo (0613)65.85
3starcoder2-15B46.95
4CodeQwen1.5-7B43.9
5starcoder2-7B36.59

Interactive version: theaggregate.ai/benchmark?slug=big-code-memorization · How It Works · Data refreshed daily, snapshot 2026-09-05.