LIVE

Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|

code

Best self-hosted coding LLM

Open-weight models specialised in or strong at programming, for an internal coding assistant, automated review or a CI agent, with source code never leaving the company.

#	Model	Arena Elo	RAM (Q4)	Hosting	Licence
1	🇨🇳Kimi K2.6 Moonshot AI	1461	—	Self-hostable	modified-mit
2	🇨🇳GLM-5 Zhipu AI	1458	—	Self-hostable	apache-2.0
3	🇺🇸Gemma 4 31B Google	1451	21 Go	Self-hostable	apache-2.0
4	🇺🇸Gemma 4 26B-A4B Google	1438	18 Go	Self-hostable	apache-2.0
5	🇫🇷Mistral Large 3 Mistral AI	1414	425 Go	Self-hostable	apache-2.0
6	🇨🇳GLM-4.5 Z.ai	1411	225 Go	Self-hostable	mit
7	🇨🇳DeepSeek-R1 DeepSeek	1398	423 Go	Self-hostable	mit
8	🇨🇳DeepSeek V3 DeepSeek	1396	431 Go	Self-hostable	mit
9	🇨🇳Qwen3-Coder 480B Alibaba	1387	303 Go	Self-hostable	apache-2.0
10	🇨🇳DeepSeek R2 DeepSeek	1370	—	Self-hostable	mit

Data verified on 4 September 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