LLM Stats

LLM Stats is an AI leaderboard that ranks over 300 models based on intelligence, speed, and price metrics derived from public benchmarks and live API data.

LLM Stats provides an independent leaderboard for comparing AI models, including GPT, Claude, Gemini, Llama, DeepSeek, Qwen, Mistral, and GLM. It calculates a composite LLM Stats Score by aggregating data from public benchmarks and live API performance metrics. Users can filter rankings to identify models based on intelligence, output speed, and cost per million tokens. The platform tracks specific model characteristics like reasoning capabilities, coding performance, context window sizes, and open-weight status. It serves as a tool for researchers and developers to choose, compare, and interpret current leading AI models.

LLM Stats at a glance

Best for: Software engineer, Researcher
Runs on: Web
Pricing: Free
Released: November 2024
Category: AI research tool
Website: llm-stats.com

Key features

Composite LLM Stats Score calculation
Continuous updates from public benchmarks
Live API metric integration
Advanced filtering for model comparison
Tracking of reasoning, coding, and speed metrics
Categorization by intelligence, speed, and price

Use it for

Comparing performance of top AI models
Finding the most cost-effective models
Identifying models with specific capabilities like large context windows
Evaluating model reasoning and coding benchmarks

Alternatives to LLM Stats

LM Arena — Compare anonymous AI models blindly and vote on the best outputs.
llm-d — Deploys production-grade LLM serving on existing hardware clusters.
AirLLM — Runs massive 70B+ parameter models on small 4GB consumer GPUs.
LLM Wiki Research — Compiles parallel agent research into source-backed markdown knowledge bases.
WebLLM — Runs high-performance language models directly inside web browsers.
vLLM — Maximizes throughput with PagedAttention and continuous batching.
MLC LLM — Enables native optimization and deployment of AI models across platforms.
LLM CLI — It enables command-line interaction with remote APIs and local machine models.
OpenCompass — It offers an objective, comprehensive, and credible open-source AI evaluation system.
llmware — Build private, local RAG pipelines with 300+ prepackaged models and integrated document parsing.
OpenLLM — It simplifies infrastructure management and optimizes inference speed and cost.
LiteLLM — One OpenAI-format API for 100+ LLM providers

All LLM Stats alternatives