Generate README Eval — leaderboard

Benchmark for generating structured README files from entire GitHub repositories, evaluating long-context codebase summarization with BLEU, ROUGE, semantic similarity, structure, information retrieval, code consistency, and readability metrics.

Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 14 models tracked.

Top models

#ModelScore
1Gemini 1.5 Flash (Preview 0827)33.43
2GPT-4o33.13
3O1 Mini (2024-09-12)33.05
4Gemini 1.5 Pro (Preview 0827)32.51
5GPT-4o Mini32.16
6Gemini 1.5 Flash-8B32.12
7Llama 3.1 8B Instruct24.43

Interactive version: theaggregate.ai/benchmark?slug=generate-readme-eval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.