DEPRECATED - Updates and contributions

This repository is now depracated and won't be getting any new updates. For contributions and corrections of the data seen in LLM Stats please create a post with the tag "Issue" in the official community section of the website.

For model and/or benchmark specific corrections, please visit create an Issue under the "Discussion" tab of the model/benchmark, as seen in the example below.

---

LLM-Stats.com

A community-driven repository of LLM data and benchmarks. Compare and explore language models through our interactive dashboard at llm-stats.com.

Found an issue or have a feature request?

Open an issue here. Thank you!

Data

🔍 What's Inside

Our repository contains detailed information on hundreds of LLMs:

• Model parameters, context window sizes, licensing details, capabilities, and more
• Provider pricing and configurations
• Performance metrics (throughput, latency)
• Standardized benchmark results
• Organization and license information

📁 Data Structure

All data is organized in the data/ directory:

• data/models/ - Model metadata and configurations
• data/providers/ - Provider information
• data/provider_models/ - Provider-specific model pricing and features
• data/benchmarks/ - Benchmark definitions
• data/model_benchmarks/ - Model benchmark scores
• data/organizations/ - Organization information
• data/licenses/ - License definitions

🤝 How to Contribute

We welcome community contributions to keep our data accurate and up-to-date:

1. Update Model Data

   • Browse the data/ directory structure
   • Submit a PR following our contribution guidelines
   • Check schemas/ for JSON Schema validation

📈 Data Quality

Accuracy is our priority. To ensure reliable information:

• All benchmark data requires verifiable source links
• Community review process for all changes
• Multiple source citations encouraged
• Regular validation of submitted data

There's no guarantee that the data is 100% accurate, but we do our best to ensure it's as accurate as possible.

🌟 Community

• Join our Discord for discussions

Leaderboard

Name	Release Date	Input Context	Output Context	GPQA	MMLU	MMLU-Pro	MATH	HumanEval	MMMU	LiveCodeBench
GPT-5	2025-08-07	N/A	N/A	0.857	0.925	N/A	0.847	0.934	0.842	N/A
o1	2024-12-17	N/A	N/A	0.780	0.918	N/A	0.964	0.881	0.776	N/A
GPT-4.5	2025-02-27	N/A	N/A	0.695	0.908	N/A	N/A	0.880	0.752	N/A
o1-preview	2024-09-12	N/A	N/A	0.733	0.908	N/A	0.855	N/A	N/A	N/A
Claude 3.5 Sonnet	2024-10-22	N/A	N/A	0.672	0.904	0.776	0.783	0.937	0.683	N/A
Claude 3.5 Sonnet	2024-06-21	N/A	N/A	0.594	0.904	0.761	0.711	0.920	N/A	N/A
Kimi K2 0905