REASONING

A new paper shows a 3B parameter model hitting 94.3 on AIME26 and 96.1% on LeetCode contests - matching or exceeding models 100x its size. The catch: it traded general knowledge for pure reasoning ability.

Anthropic's first generally available Mythos-class model, released June 9, 2026. 1M context, 128K max output, $10/$50 per million tokens. Built for long-horizon agentic work.

A production guide to Claude's extended thinking mode. Real cost math, TypeScript SDK code, and the tasks where reasoning tokens are worth 3x the spend.

Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token context window. Available via API and in Claude Code.

DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.

Low, medium, high, xhigh, and max for adaptive reasoning control.

Google's frontier model family. Gemini 2.5 Pro has 1M token context and top-tier coding benchmarks. Gemini 3 Pro pushes reasoning further. Free tier via AI Studio.

xAI's model with real-time X/Twitter data access. Grok 3 rivals top models on reasoning. Built-in web search and current events awareness. Available via API.

OpenAI's latest flagship model. Major leap in reasoning, coding, and instruction following over GPT-4o. Powers ChatGPT Plus/Pro and the API. Available via API and ChatGPT.

Open-source reasoning models from China. DeepSeek-R1 rivals o1 on math and code benchmarks. V3 for general use. Fully open weights. Extremely cost-effective API.

OpenAI's flagship. GPT-4o for general use, o3 for reasoning, Codex for coding. 300M+ weekly users. Tasks, agents, web browsing, DALL-E, code interpreter.

Anthropic's AI. Opus 4.6 for hard problems, Sonnet 4.6 for speed, Haiku 4.5 for cost. 200K context window. Best coding model I've tested. Max plan ($200/mo).