Technology

LLMstats

LLM Stats is an independent, community-driven directory and leaderboard for comparing over 300 AI models across intelligence, speed, and API pricing.

LLM Stats simplifies model selection by evaluating more than 300 large language models (including GPT, Claude, Gemini, and Llama) on a single, unified scoring system. The platform aggregates live API metrics and public benchmarks (such as SWE-bench, MMLU, and GPQA) to rank models by intelligence, throughput speed, and input/output pricing. By offering side-by-side comparisons, interactive playgrounds, and granular filtering for parameters like context window size and self-hosting viability, LLM Stats helps developers balance the critical tradeoffs of capability, cost, and latency.