Eva Unit 01
Inclusionai
Thinkingmachines
Bytedance
Sakana
Soob3123
Heabsy
Inception
Liquid
Moondream
Write and fix code
“Refactor this module and add tests”
Claude Fable 5.1Top pick ·50.1%Ranked by NanoGPT CompositePrivate AI
Text, image, video, 3D and audio models from every major lab. Compare them, see what everyone is using, and start with the best one for your task.
The text models NanoGPT users run the most right now.
#1 Claude Opus 5.5Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.
#2 Abliterated Model Large V2Abliteration.ai's default unrestricted large text reasoning model is derived from GLM-5.3 and weight-modified to reduce refusals compared with the base model. It supports native tool calling, structured output, automatic prompt caching, and a one-million-token context window.
#3 GLM 5.3 UncensoredAn experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.
The newest models across every type.
What people actually use on NanoGPT, and how models score on independent benchmarks.
Text model usage share
Weekly share of NanoGPT usage over the last 26 weeks
Videos
Full rankingTop picks per task, ranked by independent benchmarks and refreshed automatically.
“Refactor this module and add tests”
Claude Fable 5.1Top pick ·50.1%Ranked by NanoGPT Composite“Draft a short story in the style of a noir novel”
Claude Opus 5.5Top pick ·81.0%Ranked by NanoGPT Composite“Stay in character as a ship captain”
Claude Opus 5Top pick ·96.9%Ranked by NanoGPT Composite“Prove this inequality step by step”
Gemini 4 ArgonTop pick ·50.0%Ranked by NanoGPT Composite“A product shot on marble, soft morning light”
GPT Image 2.5 SunburstTop pick ·1222 EloRanked by Artificial Analysis API“Swap the background for a beach at sunset”
GPT Image 2.5 SunburstTop pick ·1199 EloRanked by Artificial Analysis API“A drone shot over a foggy forest at dawn”
Wan 3.0 Text-to-VideoTop pick ·1134 EloRanked by Artificial Analysis API“Bring this portrait to life with a slow smile”
Gemini Omni FlashTop pick ·1368 EloRanked by Artificial Analysis APISample outputs from the newest image and video models. Click one to try it.
Model families from the labs that trained them.
Qwen
80 models
OpenAI
57 models
Z.AI
39 models
Anthropic
32 models
24 models
Mistral
21 models
DeepSeek
19 models
Moonshot AI
12 models
MiniMax
11 models
NVIDIA
11 models
Xiaomi
10 models
Meta
8 models
xAI
8 models
Aion Labs
6 models
Upstage
5 models
Eva Unit 01
4 models
Inclusionai
4 models
Thinkingmachines
4 models
Amazon
3 models
Bytedance
3 models
Nous Research
3 models
