GitHub HydraFusion: Multi-Model Copilot Routing 2026
September 14, 2026
GitHub's HydraFusion can route one coding prompt across several models at runtime. Its own table shows cost down on all three benchmarks and quality up on one.
#agentic-coding
Coding Agents vs SaaS: The 2026 Build-vs-Buy Shift
September 4, 2026
32% of respondents told McKinsey their org skipped a software purchase because coding agents could build it. What that number measures, and what it does not.
Kimi K3 vs Fable 5, GPT-5.6, Grok: 2026 Benchmarks
July 22, 2026
Kimi K3 is the first open 3T-class model. See how Moonshot's launch benchmarks stack up against Claude Fable 5, GPT-5.6 Sol, Grok 4.5, and Gemini in 2026.
Claude Sonnet 5: Cheaper Agents, Near-Opus Power (2026)
July 1, 2026
Claude Sonnet 5 brings near-Opus 4.8 agentic coding at $2/$10 per million tokens through August. See the pricing, the tokenizer catch, and the system card.
Kimi K2.7-Code: Open Weights, First-Party Numbers (2026)
June 13, 2026
Moonshot's Kimi K2.7-Code is a 1T open-weight coding model with cheap API pricing, but every launch benchmark is first-party. Here's what's actually verified.
DeepSWE: AI Coding Benchmark Catches Claude Cheating in 2026
May 28, 2026
Datacurve's DeepSWE coding benchmark crowns GPT-5.5 at 70%, catches Claude Opus 4.7 reading gold commits from .git history, and exposes SWE-Bench Pro flaws.
Google Antigravity 2.0: Agentic Coding Platform 2026
May 25, 2026
Google Antigravity 2.0 expands Google's agentic coding tool into a platform: a desktop app, the Antigravity CLI, an SDK, and Managed Agents in the Gemini API.
China's Open-Weight Coding Wave: 4 Models, 18 Days
May 17, 2026
Four Chinese labs shipped open-weight coding models in 18 days. Inside the benchmarks, prices, and architectures reshaping agentic coding economics in 2026.
Chinese Open-Weight Coding LLMs: 2026's Three-Week Sweep
May 11, 2026
In 17 days, GLM-5.1, Kimi K2.6, and DeepSeek V4 shipped frontier-tier open-weight coding LLMs at a fraction of Western prices. Inside the April 2026 wave.