LIVE
Anthropic says Claude helped trace the origin of NIST's mysterious ECDSA seeds16/10/26 · Anthropic|Reflection AI unveils Beam, a 501-billion-parameter open model16/10/26 · Reflection AI|Meta releases Muse Spark Open, a mixture-of-experts model built for local Mac Studio inference15/10/26 · Meta|Meta releases Muse Spark Open, an open-weight multimodal model15/10/26 · Meta|Google DeepMind outlines safety measures behind Gemini 4 Argon13/10/26 · Google DeepMind|Tev-Gym: A Training Recipe to Fix Sparse Rewards in Long-Horizon Agents13/10/26|Google DeepMind references Gemini 4, code-named Argon13/10/26 · Google DeepMind|Google DeepMind unveils Gemini 4 Argon, a robotics-focused variant13/10/26 · Google DeepMind|Character.AI files for Chapter 11 bankruptcy, sells assets to Disney13/10/26 · Character.AI|Study Shows AI Models Can Provably Conceal Arbitrary Capabilities13/10/26|A Goodfire researcher reignites debate over how to understand neural networks19/10/26 · Goodfire|CERN and Mistral AI sign statement of intent for scientific AI partnership19/10/26 · Mistral AI|Anthropic says Claude helped trace the origin of NIST's mysterious ECDSA seeds16/10/26 · Anthropic|Reflection AI unveils Beam, a 501-billion-parameter open model16/10/26 · Reflection AI|Meta releases Muse Spark Open, a mixture-of-experts model built for local Mac Studio inference15/10/26 · Meta|Meta releases Muse Spark Open, an open-weight multimodal model15/10/26 · Meta|Google DeepMind outlines safety measures behind Gemini 4 Argon13/10/26 · Google DeepMind|Tev-Gym: A Training Recipe to Fix Sparse Rewards in Long-Horizon Agents13/10/26|Google DeepMind references Gemini 4, code-named Argon13/10/26 · Google DeepMind|Google DeepMind unveils Gemini 4 Argon, a robotics-focused variant13/10/26 · Google DeepMind|Character.AI files for Chapter 11 bankruptcy, sells assets to Disney13/10/26 · Character.AI|Study Shows AI Models Can Provably Conceal Arbitrary Capabilities13/10/26|A Goodfire researcher reignites debate over how to understand neural networks19/10/26 · Goodfire|CERN and Mistral AI sign statement of intent for scientific AI partnership19/10/26 · Mistral AI|
FR

Best LLMs for French

Models built or trained with French as a first-class language: French and European vendors, plus multilingual models where French is not an afterthought. Ranked by Elo, all hosting modes included.

#ModelArena EloContextHostingLicence
1🇨🇳Qwen3.7 Max
Alibaba
14741MAPIproprietary
2🇨🇳GLM-5
Zhipu AI
1457200KSelf-hostableMIT
3🇨🇳Qwen3.5 397B-A17B
Alibaba
1442262KSelf-hostableapache-2.0
4🇨🇳Qwen 3 Max
Alibaba
1434256KEU optionproprietary
5🇫🇷Mistral Large 4
Mistral AI
14320APIunknown
6🇺🇸Nemotron 3 Ultra 550B-A55B
NVIDIA
14261MSelf-hostableopenmdw-1.1
7🇫🇷Mistral Medium 3.5
Mistral AI
1426262KSelf-hostablemodified-mit
8🇫🇷Mistral Large 3
Mistral AI
1414256KSelf-hostableapache-2.0
9🇨🇳Qwen3 235B-A22B
Alibaba
1375128KSelf-hostableapache-2.0
10🇺🇸Nemotron 3 Super 120B-A12B
NVIDIA
13601MSelf-hostablenvidia-open-model
Data verified on 19 October 2026Open in the comparator

Method

Deterministic ranking on comparator data: LMArena Elo (style control) first, HuggingFace downloads second for models without an Elo. Prices and licences are verified at the official source and dated. No model is ranked by an LLM.

Other guides