LLM Models Leaderboard

Compare the latest AI language models side by side — pricing, context windows, and capabilities from the top providers.

Frontier
Strong
Good
Efficient
An
Claude Fable 5Vision
Anthropic
Frontier1.0M$10$502026-06
An
Claude Opus 5Vision
Anthropic
Frontier1.0M$5$252026-07
An
Claude Sonnet 5Vision
Anthropic
Frontier1.0M$3$152026-05
Op
GPT-4oVisionAudio
OpenAI
Frontier128K$2.50$102024-05
Op
GPT-4.1Vision
OpenAI
Frontier1.0M$2$82025-04
Op
o3Vision
OpenAI
Frontier200K$10$402025-04
Go
Gemini 2.5 ProVisionAudio
Google
Frontier1.0M$1.25$102025-03
xA
Grok 3Vision
xAI
Frontier131K$3$152025-02
An
Claude Haiku 4.5Vision
Anthropic
Strong200K$1$52025-10
Go
Gemini 2.5 FlashVisionAudio
Google
Strong1.0M$0.15$0.602025-04
Me
Llama 4 MaverickVision
Meta
Strong1.0M$0.20$0.602025-04
Mi
Mistral LargeVision
Mistral
Strong131K$2$62024-11
De
DeepSeek R1
DeepSeek
Strong164K$0.55$2.192025-01
De
DeepSeek V3
DeepSeek
Strong164K$0.27$1.102025-03
Go
Gemini 2.0 FlashVisionAudio
Google
Good1.0M$0.10$0.402025-02
Me
Llama 3.3 70B
Meta
Good131K$0.18$0.362024-12
Co
Command R+
Cohere
Good128K$2.50$102024-04
xA
Grok 3 MiniVision
xAI
Good131K$0.30$0.502025-02
Op
GPT-4o MiniVision
OpenAI
Efficient128K$0.15$0.602024-07
Mi
Mistral SmallVision
Mistral
Efficient131K$0.10$0.302025-01

Prices are per 1M tokens in USD. Data sourced from manual research. Context window in tokens.