List of All LLM Models
Discover and compare 500+ large language models with real-time rankings, benchmarks, and community votes.
Meta: Llama 4 Maverick
By Meta Llama
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.
Release Date
05 Apr 2025
Context Size
1.05M
Meta: Llama 4 Scout
By Meta Llama
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.
Release Date
05 Apr 2025
Context Size
327.68K
Quasar Alpha
By OpenRouter
This is a cloaked model provided to the community to gather feedback. It’s a powerful, all-purpose model supporting long-context tasks, including code generation. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.
Release Date
02 Apr 2025
Context Size
1M
OpenHands LM 32B V0.1
By all-hands
OpenHands LM v0.1 is a 32B open-source coding model fine-tuned from Qwen2.5-Coder-32B-Instruct using reinforcement learning techniques outlined in SWE-Gym. It is optimized for autonomous software development agents and achieves strong performance on SWE-Bench Verified, with a 37.2% resolve rate. The model supports a 128K token context window, making it well-suited for long-horizon code reasoning and large codebase tasks. OpenHands LM is designed for local deployment and runs on consumer-grade GPUs such as a single 3090. It enables fully offline agent workflows without dependency on proprietary APIs. This release is intended as a research preview, and future updates aim to improve generalizability, reduce repetition, and offer smaller variants.
Release Date
02 Apr 2025
Context Size
131.07K
DeepSeek: DeepSeek V3 Base
By DeepSeek
Note that this is a base model mostly meant for testing, you need to provide detailed prompts for the model to return useful responses. DeepSeek-V3 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks. DeepSeek-V3 Base is the pre-trained model behind [DeepSeek V3](/deepseek/deepseek-chat-v3)
Release Date
29 Mar 2025
Context Size
131.07K
Typhoon2 8B Instruct
By scb10x
Llama3.1-Typhoon2-8B-Instruct is a Thai-English instruction-tuned model with 8 billion parameters, built on Llama 3.1. It significantly improves over its base model in Thai reasoning, instruction-following, and function-calling tasks, while maintaining competitive English performance. The model is optimized for bilingual interaction and performs well on Thai-English code-switching, MT-Bench, IFEval, and tool-use benchmarks. Despite its smaller size, it demonstrates strong generalization across math, coding, and multilingual benchmarks, outperforming comparable 8B models across most Thai-specific tasks. Full benchmark results and methodology are available in the [technical report.](https://arxiv.org/abs/2412.13702)
Release Date
28 Mar 2025
Context Size
8.19K
Typhoon2 70B Instruct
By scb10x
Llama3.1-Typhoon2-70B-Instruct is a Thai-English instruction-tuned language model with 70 billion parameters, built on Llama 3.1. It demonstrates strong performance across general instruction-following, math, coding, and tool-use tasks, with state-of-the-art results in Thai-specific benchmarks such as IFEval, MT-Bench, and Thai-English code-switching. The model excels in bilingual reasoning and function-calling scenarios, offering high accuracy across diverse domains. Comparative evaluations show consistent improvements over prior Thai LLMs and other Llama-based baselines. Full results and methodology are available in the [technical report.](https://arxiv.org/abs/2412.13702)
Release Date
28 Mar 2025
Context Size
8.19K
Bytedance: UI-TARS 72B
By bytedance-research
UI-TARS 72B is an open-source multimodal AI model designed specifically for automating browser and desktop tasks through visual interaction and control. The model is built with a specialized vision architecture enabling accurate interpretation and manipulation of on-screen visual data. It supports automation tasks within web browsers as well as desktop applications, including Microsoft Office and VS Code. Core capabilities include intelligent screen detection, predictive action modeling, and efficient handling of repetitive interactions. UI-TARS employs supervised fine-tuning (SFT) tailored explicitly for computer control scenarios. It can be deployed locally or accessed via Hugging Face for demonstration purposes. Intended use cases encompass workflow automation, task scripting, and interactive desktop control applications.
Release Date
26 Mar 2025
Context Size
32.77K
Qwen: Qwen2.5 VL 3B Instruct
By Qwen
Qwen2.5 VL 3B is a multimodal LLM from the Qwen Team with the following key enhancements: - SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc. - Agent that can operate your mobiles, robots, etc.: with the abilities of complex reasoning and decision making, Qwen2.5-VL can be integrated with devices like mobile phones, robots, etc., for automatic operation based on visual environment and text instructions. - Multilingual Support: to serve global users, besides English and Chinese, Qwen2.5-VL now supports the understanding of texts in different languages inside images, including most European languages, Japanese, Korean, Arabic, Vietnamese, etc. For more details, see this [blog post](https://qwenlm.github.io/blog/qwen2-vl/) and [GitHub repo](https://github.com/QwenLM/Qwen2-VL). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).
Release Date
26 Mar 2025
Context Size
64K
Google: Gemini 2.5 Pro Experimental
By Google
This model has been deprecated by Google in favor of the (paid Preview model)[google/gemini-2.5-pro-preview] Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.
Release Date
25 Mar 2025
Context Size
1.05M
Qwen: Qwen2.5 VL 32B Instruct
By Qwen
Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It excels at visual analysis tasks, including object recognition, textual interpretation within images, and precise event localization in extended videos. Qwen2.5-VL-32B demonstrates state-of-the-art performance across multimodal benchmarks such as MMMU, MathVista, and VideoMME, while maintaining strong reasoning and clarity in text-based tasks like MMLU, mathematical problem-solving, and code generation.
Release Date
24 Mar 2025
Context Size
32.77K
DeepSeek: DeepSeek V3 0324
By DeepSeek
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
Release Date
24 Mar 2025
Context Size
163.84K
Qrwkv 72B
By featherless
Qrwkv-72B is a linear-attention RWKV variant of the Qwen 2.5 72B model, optimized to significantly reduce computational cost at scale. Leveraging linear attention, it achieves substantial inference speedups (>1000x) while retaining competitive accuracy on common benchmarks like ARC, HellaSwag, Lambada, and MMLU. It inherits knowledge and language support from Qwen 2.5, supporting approximately 30 languages, making it suitable for efficient inference in large-context applications.
Release Date
20 Mar 2025
Context Size
32.77K
OpenAI: o1-pro
By OpenAI
The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.
Release Date
19 Mar 2025
Context Size
200K
Mistral: Mistral Small 3.1 24B
By Mistral AI
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)
Release Date
17 Mar 2025
Context Size
128K
OlympicCoder 32B
By open-r1
OlympicCoder-32B is a high-performing open-source model fine-tuned using the CodeForces-CoTs dataset, containing approximately 100,000 chain-of-thought programming samples. It excels at complex competitive programming benchmarks, such as IOI 2024 and Codeforces-style challenges, frequently surpassing state-of-the-art closed-source models. OlympicCoder-32B provides advanced reasoning, coherent multi-step problem-solving, and robust code generation capabilities, demonstrating significant potential for olympiad-level competitive programming applications.
Release Date
15 Mar 2025
Context Size
32.77K
SteelSkull: L3.3 Electra R1 70B
By steelskull
L3.3-Electra-R1-70 is the newest release of the Unnamed series. Built on a DeepSeek R1 Distill base, Electra-R1 integrates various models together to provide an intelligent and coherent model capable of providing deep character insights. Through proper prompting, the model demonstrates advanced reasoning capabilities and unprompted exploration of character inner thoughts and motivations. Read more about the model and [prompting here](https://huggingface.co/Steelskull/L3.3-Electra-R1-70b)
Release Date
15 Mar 2025
Context Size
128K
AllenAI: Olmo 2 32B Instruct
By Ai2
OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks such as GSM8K, MATH, IFEval, and general NLP evaluation. Developed by AI2, OLMo-2 32B is part of an open, research-oriented initiative, trained primarily on English-language datasets to advance the understanding and development of open-source language models.
Release Date
14 Mar 2025
Context Size
128K
Google: Gemma 3 1B
By Google
Gemma 3 1B is the smallest of the new Gemma 3 family. It handles context windows up to 32k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Note: Gemma 3 1B is not multimodal. For the smallest multimodal Gemma 3 model, please see [Gemma 3 4B](google/gemma-3-4b-it)
Release Date
14 Mar 2025
Context Size
32K
Google: Gemma 3 4B
By Google
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.
Release Date
13 Mar 2025
Context Size
131.07K
AI21: Jamba 1.6 Large
By AI21
AI21 Jamba Large 1.6 is a high-performance hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. Developed by AI21, it excels in extremely long-context handling (256K tokens), demonstrates superior inference efficiency (up to 2.5x faster than comparable models), and supports structured JSON output and tool-use capabilities. It has 94 billion active parameters (398 billion total), optimized quantization support (ExpertsInt8), and multilingual proficiency in languages such as English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew. Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
Release Date
13 Mar 2025
Context Size
256K
AI21: Jamba Mini 1.6
By AI21
AI21 Jamba Mini 1.6 is a hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. With 12 billion active parameters (52 billion total), this model excels in extremely long-context tasks (up to 256K tokens) and achieves superior inference efficiency, outperforming comparable open models on tasks such as retrieval-augmented generation (RAG) and grounded question answering. Jamba Mini 1.6 supports multilingual tasks across English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew, along with structured JSON output and tool-use capabilities. Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
Release Date
13 Mar 2025
Context Size
256K
Google: Gemma 3 12B
By Google
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)
Release Date
13 Mar 2025
Context Size
131.07K
Cohere: Command A
By Cohere
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.
Release Date
13 Mar 2025
Context Size
256K
OpenAI: GPT-4o-mini Search Preview
By OpenAI
GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
Release Date
12 Mar 2025
Context Size
128K
OpenAI: GPT-4o Search Preview
By OpenAI
GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
Release Date
12 Mar 2025
Context Size
128K
Reka Flash 3
By rekaai
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags ("<reasoning>") to indicate its internal thought process. Reka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.
Release Date
12 Mar 2025
Context Size
65.54K
Google: Gemma 3 27B
By Google
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)
Release Date
12 Mar 2025
Context Size
131.07K
LatitudeGames: Wayfarer Large 70B Llama 3.3
By latitudegames
Wayfarer Large 70B is a roleplay and text-adventure model fine-tuned from Meta’s Llama-3.3-70B-Instruct. Specifically optimized for narrative-driven, challenging scenarios, it introduces realistic stakes, conflicts, and consequences often avoided by standard RLHF-aligned models. Trained using a curated blend of adventure, roleplay, and instructive fiction datasets, Wayfarer emphasizes tense storytelling, authentic player failure scenarios, and robust narrative immersion, making it uniquely suited for interactive fiction and gaming experiences.
Release Date
10 Mar 2025
Context Size
128K
TheDrummer: Skyfall 36B V2
By Drummer
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
Release Date
10 Mar 2025
Context Size
32.77K
Showing page 15 of 25 with 737 models total