News
EveryLLM

Many languages

Trained across dozens of languages. 295 models on EveryLLM so far.

Multilingual models are trained across dozens or hundreds of languages and can answer, translate and switch between them. Because the web is dominated by English, builders must sample other languages more heavily, collect new data and design tokenizers that do not split non-Latin scripts into too many pieces. Skills learned in one language often transfer to others, so a multilingual model can do things in Swahili that it mostly learned in English.

Coverage keeps widening

BLOOM (2022) covered 46 natural languages and 13 programming languages. Meta's Llama 3.1 (2024) officially supported eight languages, while Google's Gemma 3 (March 2025) claimed over 140 and Alibaba's Qwen3 (April 2025) 119 languages and dialects. Switzerland's Apertus (September 2025) was trained on text in more than 1,800 languages. Cohere's Aya project (2024) gathered instruction data in 101 languages with help from about 3,000 researchers worldwide.

Gaps that remain

Benchmarks show that quality still drops in languages with little online text, and translated test sets can hide cultural mistakes. The same sentence can need several times more tokens in Hindi, Tamil or Amharic than in English, which makes it slower and dearer to process. Tokenizers have improved: OpenAI's GPT-4o tokenizer (2024) sharply cut token counts for Indian scripts such as Gujarati, Telugu and Hindi.

Famous many languages models

Still to be written: GPT-4o.

Further reading

MiMo-V2.5-Pro 馃嚚馃嚦 ChinaMiMo-V2.5-Pro Open-source MoE language model with 1M token contextGeneral 路 Open weights fnGranite 4.0 馃嚭馃嚫 United StatesGranite 4.0 IBM's hybrid Mamba/transformer language models for enterprise workGeneral 路 Open weights 路 2025 fnSolar Open 2 馃嚢馃嚪 South KoreaSolar Open 2 250B parameter open-weight model for agentic tasksGeneral 路 Open weights 路 2026 RecurrentGemma 馃嚭馃嚫 United StatesRecurrentGemma Open language models using Google's Griffin recurrent-plus-attention architectureGeneral 路 Open weights 路 2024 MiMo-V2-Flash 馃嚚馃嚦 ChinaMiMo-V2-Flash High-speed MoE language model for reasoning and agentsGeneral 路 Open weights fnNemotron Nano 2 馃嚭馃嚫 United StatesNemotron Nano 2 A 9B hybrid Mamba-Transformer model for reasoning and chat, from NVIDIA.General 路 Open weights 路 2025 fnNemotron 3 Super 馃嚭馃嚫 United StatesNemotron 3 Super NVIDIA's 120B hybrid MoE language model with 12B active parameters and 1M-token contextGeneral 路 Conditional licence 路 2026 fnLFM2 馃嚭馃嚫 United StatesLFM2 Hybrid language models for edge and on-device useSmall 路 Open weights fnQwen3-Next-80B-A3B 馃嚚馃嚦 ChinaQwen3-Next-80B-A3B An 80-billion parameter hybrid model with ultra-long context support.General 路 Open weights imgfnQwen3.5-397B-A17B 馃嚚馃嚦 ChinaQwen3.5-397B-A17B A large multimodal language model with sparse activation.General 路 Open weights fnEXAONE 4.0 馃嚢馃嚪 South KoreaEXAONE 4.0 Unified language model with reasoning and non-reasoning modesGeneral 路 Conditional licence 路 2025 Falcon-H1R-7B 馃嚘馃嚜 United Arab EmiratesFalcon-H1R-7B A 7-billion parameter reasoning model with hybrid architectureReasoning 路 Open weights 路 2026 Falcon-H1 馃嚘馃嚜 United Arab EmiratesFalcon-H1 Hybrid transformer and state-space model series by TIIGeneral 路 Open weights 路 2025 Kimi Linear 馃嚚馃嚦 ChinaKimi Linear Hybrid linear attention model with 48 billion parametersGeneral 路 Open weights 路 2025 MiniMax-Text-01 馃嚚馃嚦 ChinaMiniMax-Text-01 A large language model with a four million token context window.General 路 Open weights 路 2025 ERNIE 3.0 馃嚚馃嚦 ChinaERNIE 3.0 Knowledge-enhanced pre-training model for language tasksGeneral 路 Research only 路 2021 Hunyuan-TurboS 馃嚚馃嚦 ChinaHunyuan-TurboS Hybrid Mamba-Transformer MoE model by TencentGeneral 路 API only 路 2025 Jamba 馃嚠馃嚤 IsraelJamba Hybrid open-weights language model with long contextGeneral 路 Open weights 路 2024

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.