REASONING
12 items
2 posts, 9 tools, 1 guide
VibeThinker-3B is a 3B parameter reasoning model reporting 94.3% on AIME 2026. What the paper claims, how to run it locally, and what it trades away.
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 Opus model released April 2026, since succeeded by Opus 4.8 and Opus 5.5. Strong at coding, long-context analysis, and agentic work. 1M context, $5/$25 per million tokens.
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.
Google's model family. As of October 2026 Gemini 4 Argon (GA October 13, 1M token context) is the flagship for coding and agents, with Gemini 3.8 Flash (free tier in AI Studio) as the fast, cheaper option.
Chinese lab shipping open-weight MoE models. The V4 family (previewed April 24, 2026) runs a 1M context on DeepSeek's API; R1 (2025) popularized open reasoning models. Low-cost API.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.