AI Benchmarks & Rankings
AI Model Rankings
Comprehensive benchmarks across models, agents, and tools \u2014 updated daily
GPT-5.2
OpenAI
96.8
Overall Score
up
General
Claude 4.6 Opus
Anthropic
95.2
Overall Score
up
Reasoning
Gemini 3.1 Ultra
94.7
Overall Score
same
Multimodal
Rank
Model
Provider
Category
Score
Trend
GPT-5.2
OpenAI
General
96.8
Claude 4.6 Opus
Anthropic
Reasoning
95.2
Gemini 3.1 Ultra
Google
Multimodal
94.7
4
Qwen3.5-Omni
Alibaba
Multilingual
93.1
5
DeepSeek-V3
DeepSeek
Code
92.4
6
Llama 4 Scout
Meta
Open Source
91.8
7
Mistral Large 3
Mistral
European
90.5
8
Grok-3
xAI
General
89.9
9
Command R+
Cohere
RAG
88.7
10
Phi-4
Microsoft
Small Models
87.3