Reasoning models

4 entries between January 2025 and August 2025.

Every entry

  1. OpenAI makes GPT-5 the default model in ChatGPT

    OpenAI released GPT-5 on 7 August 2025, describing it as a unified model that combined the step-by-step reasoning of the o-series with the faster replies of the GPT series, with a 400,000-token context window. It became the default for free and paid ChatGPT users.

  2. Anthropic releases Claude Opus 4 and Claude Sonnet 4

    Anthropic released Claude Opus 4, which it called its most capable coding model, and Claude Sonnet 4 on 22 May 2025. Both offered a choice between fast replies and extended reasoning, and could search the web while reasoning. Claude Code reached general availability the same day.

  3. OpenAI ships o3, o4-mini, and the Codex CLI coding agent

    OpenAI released its o3 and o4-mini reasoning models on 16 April 2025 together with Codex CLI, an open-source coding agent that runs in a developer’s terminal, reads and edits project files, runs shell commands, and connects to external tools through the Model Context Protocol.

  4. DeepSeek releases R1, an open-weight reasoning model

    The Chinese laboratory DeepSeek released R1 on 20 January 2025, an open-weight model trained with reinforcement learning to work through problems step by step. It matched OpenAI’s o1 on several benchmarks at a small fraction of the reported training and inference cost.