Showing 1-60 of 61 articles
ARC-AGI 1
Abstraction and Reasoning Corpus for Artificial General Intelligence, version 1 Abbreviation A benchmark testing fluid intelligence and abstract reasoning...
AI BenchmarksArtificial Intelligence
Adaptive thinking
Adaptive thinking is an inference-time reasoning mode in the Anthropic Messages API in which a claude model decides, on a per-request basis, whether to use...
AI InferenceAnthropic
Agent planning
Agent planning refers to the process by which an AI agent determines a sequence of actions to accomplish a goal. In the context of large language models (LLMs)...
AI AgentsArtificial Intelligence
AlphaGeometry
AlphaGeometry is a neuro-symbolic artificial intelligence system developed by Google DeepMind that solves competition-level geometry problems at a standard...
AI ModelsAI for Science
AlphaProof
AlphaProof is a reinforcement-learning system from Google DeepMind that finds and verifies formal mathematical proofs in the Lean 4 theorem prover, and in July...
AI ModelsAI for Science
BIG-Bench Extra Hard
BIG-Bench Extra Hard (BBEH) is a reasoning benchmark released by Google DeepMind in February 2025 that replaces each of the 23 tasks in BIG-Bench Hard (BBH)...
AI BenchmarksGoogle DeepMind
Best AI Models for Reasoning and Math
As of July 2026, the strongest general reasoning models are Anthropic's Claude Opus 4.8 and Claude Fable 5, OpenAI's GPT-5.5, and Google's Gemini 3.1 Pro and...
Large Language ModelsModel Evaluation
Command A Reasoning
Command A Reasoning is an enterprise reasoning model released by Cohere on August 21, 2025, as part of the Command A family of large language models. It pairs...
AI CompaniesLarge Language Models
Commonsense reasoning
Commonsense reasoning is the ability to make the everyday, mostly tacit assumptions that ordinary humans take for granted, the implicit knowledge about how the...
Artificial Intelligence
DeepSeek V3.1
DeepSeek V3.1 is a large language model developed by DeepSeek, released on August 19, 2025 and made broadly available via the official API on August 21,...
AI ModelsChinese AI
DeepSeek-Prover
DeepSeek-Prover is a family of open-weight large language models developed by Chinese AI laboratory DeepSeek for formal theorem proving in the Lean 4 proof...
Chinese AILarge Language Models
DeepSeek-R1
DeepSeek Release date Large language model (reasoning model) Architecture DeepSeek-V3-Base (671B / 37B MoE) Parameters 128,000 tokens Training...
Chinese AILarge Language Models
DeepSeek-R1-Distill
DeepSeek-R1-Distill is a family of six open-weight reasoning language models released by DeepSeek on January 20, 2025, alongside the flagship DeepSeek-R1...
AI ModelsChinese AI
DeepSeekMath
DeepSeekMath is a family of open-weight large language models specialized for mathematical reasoning, released by Chinese AI laboratory DeepSeek in February...
Chinese AILarge Language Models
Extended thinking
Extended thinking is the product name Anthropic gives to the reasoning mode in its Claude family of large language models, in which the model produces a...
AI Tools & ProductsAnthropic
GPQA
GPQA (Graduate-Level Google-Proof Q&A) is a benchmark of 448 expert-written multiple-choice questions in biology, physics, and chemistry, designed to test...
AI Benchmarks
GPT-5 Pro
GPT-5 Pro is a large language model developed by OpenAI and the highest-capability variant of the GPT-5 model family. It is positioned above the standard GPT-5...
Large Language ModelsOpenAI
GRPO
Group Relative Policy Optimization (GRPO) is a reinforcement learning algorithm for fine-tuning large language models that eliminates the separate critic...
AI InferenceChinese AI
GSM8K
GSM8K (Grade School Math 8K) is a benchmark dataset of 8,792 grade-school-level math word problems created by researchers at OpenAI to evaluate the multi-step...
AI BenchmarksLarge Language Models
Gemini 2.0 Flash Thinking
Gemini 2.0 Flash Thinking is an experimental reasoning model released by Google as part of the Gemini 2.0 family. First made available on December 19, 2024, it...
Google DeepMindLarge Language Models
Gemini 2.5 Deep Think
Gemini 2.5 Deep Think is Google DeepMind's enhanced reasoning mode for the Gemini 2.5 Pro model that uses a technique called "parallel thinking" to explore...
Google DeepMindLarge Language Models
Goedel-Prover
Goedel-Prover is an open-source large language model designed for automated formal theorem proving in Lean 4. Developed by researchers at Princeton Language...
Large Language ModelsOpen Source AI
Grok 4
Grok 4 is a large language model developed by xAI and released on July 9, 2025.[1] It is the fourth major generation of the Grok model family and was...
AI CompaniesAI Models
Inference-time scaling
Inference-time scaling (also called test-time compute scaling) is the practice of improving an AI model's output quality by allocating more computational...
AI InferenceAI Research
Interleaved thinking
Interleaved thinking is a feature of the Anthropic Messages API that lets Claude produce extended reasoning blocks between tool calls inside a single...
AI AgentsAnthropic
Kimi K2 Thinking
Kimi K2 Thinking is a reasoning and agentic large language model released by the Chinese startup Moonshot AI on November 6, 2025. It is a thinking variant...
Chinese AILarge Language Models
Llama Nemotron
Llama Nemotron is a family of open reasoning large language models built by Nvidia by post-training Meta's Llama models for math, coding, and agentic tasks....
Large Language ModelsNVIDIA
MAI-Thinking-1
MAI-Thinking-1 is a reasoning model developed by Microsoft AI, unveiled at Microsoft Build 2026 on June 2, 2026 as the company's first in-house flagship...
Microsoft
MATH
MATH is a benchmark of 12,500 competition mathematics problems used to evaluate the mathematical problem-solving ability of machine learning systems,...
AI BenchmarksModel Evaluation
Magistral
Magistral is the first family of reasoning models from Mistral AI, the French AI company, first released on June 10, 2025. [1] Mistral describes it as "the...
Large Language ModelsOpen Source AI
Marco-o1
Marco-o1 is an open reasoning model released in November 2024 by the MarcoPolo team at Alibaba International Digital Commerce (AIDC). It was introduced in the...
Chinese AIOpen Source AI
MathArena
MathArena: Evaluating LLMs on Uncontaminated Math Competitions Description March 2025 (USAMO 2025 evaluation), May 2025 (paper) Latest expansion Mislav...
AI BenchmarksArtificial Intelligence
MiniMax M1
MiniMax M1 (stylised MiniMax-M1) is an open-weight large language reasoning model released on 16 June 2025 by the Shanghai-based artificial-intelligence...
Chinese AILarge Language Models
MiniMax M2.7
MiniMax M2.7 is a large language model released by the Chinese AI company MiniMax on March 18, 2026.[1] It is an agentic coding and reasoning model built on a...
Chinese AILarge Language Models
MuSR
MuSR (Multistep Soft Reasoning) is a benchmark for evaluating multistep reasoning in large language models, built around long free-text narratives such as...
AI BenchmarksModel Evaluation
Muse Spark
Muse Spark is a proprietary multimodal reasoning model developed by Meta Superintelligence Labs (MSL), the artificial intelligence division Meta reorganized in...
Meta AIMultimodal AI
Natural language inference (NLI)
Natural language inference (NLI), also known as recognising textual entailment (RTE), is the natural language processing task of deciding whether a hypothesis...
AI BenchmarksNatural Language Processing
OLMo 3
OLMo 3 is the third generation of fully open language models released by the Allen Institute for AI (Ai2). The family was announced on November 20, 2025 and...
AI ModelsLarge Language Models
OpenAI o-series
The OpenAI o-series is a family of large language models developed by OpenAI that are trained with reinforcement learning to reason through an internal...
Artificial IntelligenceLarge Language Models
OpenAI o1
OpenAI Codename September 12, 2024 (o1-preview, o1-mini) Release date Large language model (reasoning model) Architecture o1-preview, o1-mini, o1,...
AI ModelsLarge Language Models
OpenAI o1-mini
OpenAI o1-mini is a smaller, faster, and cheaper reasoning model released by OpenAI on September 12, 2024, alongside o1-preview, and optimized for science,...
Large Language ModelsOpenAI
OpenAI o1-pro
OpenAI o1-pro is the highest-compute variant of OpenAI's o1 reasoning model, designed to spend more inference-time compute so it "thinks harder" and returns...
Large Language ModelsOpenAI
OpenAI o3
OpenAI Announced January 31, 2025 (o3-mini); April 16, 2025 (o3, o4-mini); June 10, 2025 (o3-pro); June 26, 2025 (o3-deep-research, o4-mini-deep-research) ...
AI ModelsLarge Language Models
OpenAI o3-mini
OpenAI o3-mini is a reasoning-focused large language model released by OpenAI on January 31, 2025, the second commercial member of the o-series after OpenAI o1...
Large Language ModelsOpenAI
OpenAI o3-pro
OpenAI o3-pro is a high-compute reasoning large language model released by OpenAI on June 10, 2025, designed as the professional, higher-reliability variant of...
Large Language ModelsOpenAI
Phi-4 Reasoning
Phi-4-reasoning is a 14 billion parameter open weight reasoning model released by Microsoft Research on April 30, 2025. It was launched together with...
AI ModelsLarge Language Models
Phi-4-mini-flash-reasoning
Phi-4-mini-flash-reasoning is a 3.8 billion parameter open weight reasoning model released by Microsoft in July 2025.[1] It is a latency optimized sibling of...
AI ModelsLarge Language Models
ProcessBench
ProcessBench is a benchmark for step-level verification of mathematical reasoning, built by the Qwen Team at Alibaba and released in December 2024. [1] It...
AI BenchmarksModel Evaluation
QvQ
QvQ (styled QVQ) is a family of experimental visual reasoning models from the Qwen team at Alibaba. The models extend the large language model reasoning...
Chinese AIMultimodal AI
QwQ
Alibaba Cloud Qwen team Series November 28, 2024 (QwQ-32B-Preview) Full release Large language model (reasoning model) Architecture 32.5 billion...
Chinese AILarge Language Models
RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) is a post-training paradigm for large language models in which the reward signal comes from a...
AI InferenceReinforcement Learning
ReAct (prompting)
ReAct (short for Reasoning and Acting) is a prompting paradigm for large language models that interleaves verbal reasoning traces ("Thoughts") with...
AI AgentsPrompt Engineering
Reflexion
Reflexion is a 2023 framework for reinforcing language agents through verbal self-reflection rather than weight updates: the agent reflects in natural language...
AI AgentsMachine Learning
Self-consistency
Self-consistency is a decoding strategy for large language models that samples multiple chain-of-thought reasoning paths for the same question and returns the...
Large Language ModelsPrompt Engineering
SimpleBench
SimpleBench is a text-only benchmark for large language models created by Philip, the host of the AI Explained YouTube channel, with collaborator Hemang. It...
AI BenchmarksArtificial Intelligence
Skywork-R1V
Skywork-R1V is an open-weight family of multimodal reasoning models released by Skywork AI, the AGI and AIGC division of Beijing Kunlun Tech Co., Ltd. (Kunlun...
Chinese AIMultimodal AI
Strawberry (OpenAI codename)
Strawberry was the internal codename used at OpenAI for the research program that produced the o-series of reasoning models, most notably OpenAI o1. The...
AI HistoryOpenAI
Test-time compute
Test-time compute (also called inference-time compute scaling or test-time scaling) is the practice of allocating additional computation while a large language...
Artificial IntelligenceLarge Language Models
Tree of Thoughts
Tree of Thoughts (ToT) is a prompting and inference-time search framework for large language models that lets the model explore multiple intermediate reasoning...
Artificial IntelligencePrompt Engineering
ZAYA1-8B
ZAYA1-8B is an open-weight, reasoning-focused Mixture-of-Experts (MoE) large language model released by San Francisco-based AI research lab Zyphra on May 6,...
AI ModelsLarge Language Models