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 (imported). Source: huggingface.co. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-08-06) | 33.13 | #336 |
| 2 | O1 Mini (2024-09-12) | 33.05 | #403 |
| 3 | GPT-4o Mini (2024-07-18) | 32.16 | #558 |
| 4 | Mistral Nemo Instruct (2407) | 25.62 | #936 |
| 5 | Llama 3.1 8B Instruct | 24.43 | #1035 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=generate-readme-eval · How It Works · Data refreshed daily, snapshot 2026-10-20.