Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Big Code Memorization - HumanEval-ET pass@50 — leaderboard

Metric: HumanEval-ET pass@50 (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1deepseek-coder-6.7B-instruct56.73
2GPT-3.5 Turbo (0613)47.76
3CodeQwen1.5-7B32.79
4starcoder2-15B27.95
5starcoder2-7B24.38

Interactive version: theaggregate.ai/benchmark?slug=big-code-memorization-humaneval-et-pass-50 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.