Skip to main content

Leaderboard Compare Benchmarks Models

AI Prompt WriterStart with a goal, context, and constraints Prompt OptimizerRewrite an existing prompt and inspect the diff Browse all tools›

404

Page not found

The page you're looking for doesn't exist or was moved. Try a category below — or hit ⌘K to search.

Random benchmark result

Modelo3

ByOpenAI

AAIFBENCH71.4%

Independent LLM benchmarks, pricing, and runtime evidence. Published results expose their evidence path and review date.

Supported and Estimated evidence labels

Models tracked: 296
Benchmarks: 369
Data refreshed: July 28, 2026

Tracked means a model profile exists. Supported positions have sufficiently diverse direct evidence. Estimated positions remain ranked with wider uncertainty while evidence is incomplete.

How BenchLM ranks models

Explore

LLM leaderboard Compare models Models Benchmarks Providers Best models by use case Model alternatives

Rankings

Frontier models Coding models Agentic models Reasoning models Multimodal models Best overall Best open source Best Chinese models

Dashboards

AI Race LLM pricing Price vs performance LLM speed Agent benchmarks Pricing trends LLM statistics

Research & tools

Research All tools AI prompt writer Prompt optimizer LLM selector Token counter Download data Methodology Evidence confidence Leaderboard history AI app stack

Make the right model choice this week

The model to choose, the cheaper alternative, and the release we would wait on.

Leave this field blank

I agree to receive one weekly email. Unsubscribe anytime. Privacy.

Raw benchmark rows stay exact; composite rankings use disclosed missing-data priors. © 2026 BenchLM.

About Advertise Contact Editorial policy Affiliate disclosure Privacy Terms llms.txt RSS