News
EveryLLM

Reasoning models

OpenAI o1 and o3, DeepSeek-R1 and the models that think step by step before they answer. 100 models on EveryLLM so far.

Reasoning models are language models trained to work through a problem in a long chain of intermediate steps before they give a final answer. The extra thinking tokens cost time and compute each time the model is used, but they lift results on mathematics, science and coding. OpenAI's o1, previewed in September 2024, made the approach mainstream, and DeepSeek-R1 in January 2025 showed that it could be reproduced with open weights.

Where the idea came from

Researchers at Google showed in a January 2022 paper that simply prompting a large model to write out its steps, which they called chain-of-thought prompting, improved its answers on arithmetic and logic problems. Reasoning models go further. They are trained with reinforcement learning, rewarded when a long chain of thought ends in a correct, checkable answer, so the habit of planning, checking and backtracking is built into the model itself.

The first wave

OpenAI released o1-preview on 12 September 2024 and reported that it solved 83% of problems on a qualifying exam for the International Mathematics Olympiad, against 13% for GPT-4o. DeepSeek-R1 followed on 20 January 2025 under the MIT licence, with a paper describing how reasoning emerged from large-scale reinforcement learning. Anthropic's Claude 3.7 Sonnet (February 2025) and later models let users choose how long the model thinks.

Costs and limits

A reasoning model can write thousands of hidden tokens for one question, so answers are slower and dearer to produce. Labs now train models that decide for themselves how much to think: GPT-5, released in August 2025, routes each request between a fast model and a deeper reasoning model. Researchers also debate how faithfully the visible chain of thought reflects what the network actually computes.

Famous reasoning models

Further reading

fnK-EXAONE 馃嚢馃嚪 South KoreaK-EXAONE LG AI Research multilingual Mixture-of-Experts modelGeneral 路 Open weights fnGpt-oss-120b 馃嚭馃嚫 United StatesGpt-oss-120b OpenAI's open-weight reasoning model that fits on one 80GB GPUReasoning 路 Open weights 路 2025 fnGpt-oss-20b 馃嚭馃嚫 United StatesGpt-oss-20b OpenAI's smaller open-weight reasoning model for local and low-latency useReasoning 路 Open weights 路 2025 DeepSeek-V3 馃嚚馃嚦 ChinaDeepSeek-V3 Open-weight mixture of experts language model with 671 billion parameters.General 路 Open weights 路 2024 imgwavvidQwen3-Omni 馃嚚馃嚦 ChinaQwen3-Omni Multimodal model processing text, audio, video and images with real-time speech output.Multimodal 路 Open weights 路 2025 fnKimi K2 Thinking 馃嚚馃嚦 ChinaKimi K2 Thinking Open-source reasoning model with tool use and INT4 quantizationReasoning 路 Open weights imgvidMiniMax-M3 WorldMiniMax-M3 Native multimodal model with 1M context and sparse attentionMultimodal 路 Open weights MiMo-V2-Flash 馃嚚馃嚦 ChinaMiMo-V2-Flash High-speed MoE language model for reasoning and agentsGeneral 路 Open weights fnParam-2-17B 馃嚠馃嚦 IndiaParam-2-17B Multilingual MoE model for Indian languages and reasoningGeneral 路 Open weights INTELLECT-3 WorldINTELLECT-3 Open 106B MoE reasoning model from Prime IntellectReasoning 路 Open weights fnTrinity Large 馃嚭馃嚫 United StatesTrinity Large 398B-parameter sparse MoE model family by Arcee AIGeneral 路 Open weights 路 2026 fnDeepSeek-V3.2 馃嚚馃嚦 ChinaDeepSeek-V3.2 Efficient reasoning and agentic AI model with sparse attentionReasoning 路 Open weights 路 2025 fnDeepSeek-V3.1 馃嚚馃嚦 ChinaDeepSeek-V3.1 Hybrid thinking and non-thinking language model with 671 billion parameters.General 路 Open weights DeepSeek-Prover-V2 馃嚚馃嚦 ChinaDeepSeek-Prover-V2 Open-source model for formal theorem proving in Lean 4Reasoning 路 Open weights 路 2025 fnDeepSeek-V4-Pro 馃嚚馃嚦 ChinaDeepSeek-V4-Pro 1.6T parameter MoE model with one million token contextGeneral 路 Open weights 路 2026 DeepSeek-V4-Flash 馃嚚馃嚦 ChinaDeepSeek-V4-Flash Efficient mixture-of-experts model with one million token contextGeneral 路 Open weights 路 2026 fnK-EXAONE 2.0 馃嚢馃嚪 South KoreaK-EXAONE 2.0 Open-weight multilingual language model by LG AI ResearchGeneral 路 Open weights fnQwen3-235B-A22B 馃嚚馃嚦 ChinaQwen3-235B-A22B Mixture-of-experts model with switchable reasoning modesGeneral 路 Open weights 路 2025 A.X K1 馃嚢馃嚪 South KoreaA.X K1 Sparse MoE model with controllable reasoning depthGeneral 路 Open weights 路 2026 imgvidfnQwen3-VL 馃嚚馃嚦 ChinaQwen3-VL Vision-language model with deep visual reasoning and long video context.Multimodal 路 Open weights fnKanana-2 馃嚢馃嚪 South KoreaKanana-2 Open-source multilingual model for agentic AI and reasoning.General 路 Open weights Qwen3.8-2.4T-A95B 馃嚚馃嚦 ChinaQwen3.8-2.4T-A95B Open-weight reasoning model with 2.4 trillion parametersReasoning 路 Open weights 路 2026 imgfnKimi K3.1 Pro 馃嚚馃嚦 ChinaKimi K3.1 Pro Open-weight multimodal agentic model with 1M token contextMultimodal 路 Open weights fnGLM-4.5 馃嚚馃嚦 ChinaGLM-4.5 Open-source mixture of experts model for agents and reasoningGeneral 路 Open weights 路 2025 imgfnLing-1T 馃嚚馃嚦 ChinaLing-1T Trillion-parameter efficient reasoning model by InclusionAIGeneral 路 Open weights imgLongCat-2.5 馃嚚馃嚦 ChinaLongCat-2.5 Multimodal MoE model for long-horizon agentic tasksMultimodal 路 Open weights fnMiniMax-M1 馃嚚馃嚦 ChinaMiniMax-M1 Open-weight reasoning model with hybrid attention and long contextReasoning 路 Open weights 路 2025 fnGLM-5 馃嚚馃嚦 ChinaGLM-5 Open-weight model for engineering and agentic tasksGeneral 路 Open weights 路 2026 fnERNIE-4.5-21B-A3B-Thinking 馃嚚馃嚦 ChinaERNIE-4.5-21B-A3B-Thinking Lightweight reasoning model with 21 billion parametersReasoning 路 Open weights 路 2025 fnHunyuan-A13B 馃嚚馃嚦 ChinaHunyuan-A13B Open-source MoE language model with 80 billion total parametersGeneral 路 Open weights 路 2025 imgStep3 馃嚚馃嚦 ChinaStep3 Multimodal reasoning model with 321 billion parametersMultimodal 路 Open weights 路 2025 imgvidIntern-S1 馃嚚馃嚦 ChinaIntern-S1 Open-source multimodal reasoning model for scienceReasoning 路 Open weights 路 2025 fnStep-3.5-Flash 馃嚚馃嚦 ChinaStep-3.5-Flash Open-source MoE model for reasoning and agentsGeneral 路 Open weights 路 2026 imgvidDiffusionGemma 馃嚭馃嚫 United StatesDiffusionGemma A multimodal Gemma 4 model that writes text by denoising blocks of tokens.Multimodal 路 Open weights fnSolar Open 2 馃嚢馃嚪 South KoreaSolar Open 2 250B parameter open-weight model for agentic tasksGeneral 路 Open weights 路 2026 imgvidfnKimi K2.5 馃嚚馃嚦 ChinaKimi K2.5 Open-source multimodal agentic model with vision and reasoning.Multimodal 路 Open weights Sarvam-105B 馃嚠馃嚦 IndiaSarvam-105B Open-weight MoE model for Indian languages and reasoningGeneral 路 Open weights DeepSeek-R1 馃嚚馃嚦 ChinaDeepSeek-R1 Open-weight reasoning model from ChinaReasoning 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.