LLM Stats
Independent AI evaluations lab
LLM Stats is an independent AI evaluation lab that ranks large language models across intelligence, speed, and price. It addresses the problem of comparing models scattered across different benchmarks and provider pricing by consolidating them into a single composite LLM Stats Score, updated continuously from public benchmark results and live API metrics.
The platform offers a full LLM Leaderboard with advanced filters, category-specific leaderboards for coding, writing, math, research, long context, tool calling, reasoning, image generation, and video creation, plus an Open LLM Leaderboard for models with publicly released weights. It includes a pricing comparison page covering input, cached input, output, and observed cost per turn, along with benchmark exploration across MMLU, GPQA, SWE-Bench, AIME, and others. Model detail pages provide context window, speed, and pricing data.
LLM Stats is aimed at developers, researchers, and teams selecting AI models for specific workloads. The site also offers an API and services for programmatic access to its data.
12 alternatives to LLM Stats
Ranked by how well each tool replaces LLM Stats: shared features, audience, price and popularity.
Open-source AI gateway that puts your AI stack behind one OpenAI-compatible key.
Covers 1 of 8 key features and is open source.
Free planOpen source64 out of 100 matchFree- 60 out of 100 matchContact sales
- 60 out of 100 matchFree
- 59 out of 100 matchContact sales
- 59 out of 100 match$5/mo
- 58 out of 100 matchUsage-based
An API for open models, usable locally or in the cloud
Covers 1 of 8 key features and is open source.
Free planOpen source58 out of 100 match$100/moRun efficient foundation models directly on edge devices.
Covers 1 of 8 key features and is open source.
Free planOpen source58 out of 100 matchFree- 58 out of 100 matchUsage-based
- 56 out of 100 match$250/mo
- 56 out of 100 match$1,000/mo