Claude Code retakes #1 in the AI dev tool rankings as Fable 5.1 access separates the field

September's AI dev tool power rankings put Claude Code back at #1 ahead of Cursor and Windsurf, driven entirely by its access to Claude Fable 5.1 (1762 Elo on WebDev Arena, 73 points above Fable 5) — a reminder that in AI-assisted development, the tool ranking buyers see is really a model ranking wearing a tool's name.

The latest AI dev tool power rankings have Claude Code back in first place, overtaking Cursor and Windsurf for September. The reason is specific and worth understanding rather than filing as routine leaderboard churn: Claude Code now runs on Claude Fable 5.1, which scores 1762 Elo on WebDev Arena — the highest of any model in any tool right now, and 73 points clear of the previous-generation Fable 5. Claude Opus 5, last month’s benchmark leader, sits 74 points behind at 1688. Cursor holds #3, steady since SpaceX’s $60bn acquisition closed on 14 August, and Windsurf holds #4.

The pattern behind the churn

This is the third time in three months a “best AI coding tool” ranking has flipped primarily because of which underlying model a tool gained access to, not because of a change to the tool itself. Cursor, Windsurf, and Claude Code are all, at their core, interfaces and orchestration layers wrapped around whichever frontier model they’re plugged into — so when Anthropic, OpenAI, or Google ships a new model, the rankings of tools built on top of it move even if nothing in the actual product changed that week.

Why this matters for anyone evaluating vendors

If a development partner’s pitch leans on “we use the #1-ranked AI coding tool,” it’s worth asking what’s actually driving that ranking and how quickly it could flip again — because it will. What doesn’t reset every few weeks is a team’s engineering discipline: how it reviews AI-generated code, how it structures a codebase so any model can work in it safely, and how it decides which parts of a build are suited to agentic tooling at all. That’s the layer that actually determines project outcomes, independent of which model currently tops a leaderboard.

So what

Model-of-the-month churn is a reason to evaluate a development partner on process rather than on which tool they use this quarter. See our AI-assisted development approach for how we treat these tools as one input to a build rather than the whole story, or get in touch if you want a straight answer on what a Fable 5.1-era AI-assisted build looks like for your project.

← All research

More research.

GitHub's Copilot metrics now flag developers whose usage data is missing

GitHub's 5 November 2026 changelog adds fields to the Copilot usage metrics API showing which users send no telemetry or run outdated editors. AI coding tool reporting now admits its own blind spots.

Read ›

Claude Code 2.1.323 adds experimental Code Mode and plugin version ranges

Claude Code 2.1.323 adds an opt-in Code Mode where Claude writes JavaScript to call its tools, and lets plugins declare which Claude Code versions they support. Claude Code teams get more control over extensions.

Read ›

GitHub Apps can now manage enterprise Copilot seats through the API

GitHub's 10 November 2026 changelog lets enterprise GitHub Apps assign and remove Copilot seats through a new permission. Seat management for AI coding tools can now be automated.

Read ›

GitHub will switch off Dependabot alerts on year-old inactive repositories from 8 December

From 8 December 2026, GitHub will turn off Dependabot alerts on most repositories with no activity in the past year. If you own software that is stable but unmaintained, your security alerts go quiet.

Read ›

Gemini 4 Carbon arrives in GitHub Copilot, and it can switch itself on for your whole organisation

GitHub made Gemini 4 Carbon generally available in Copilot on 10 November 2026 across ten clients. Under default model enablement, Business and Enterprise organisations get new models automatically unless an admin opts out.

Read ›

Claude Code 2.1.322 adds fast mode on Google Vertex, with a quiet fallback to standard speed

Claude Code 2.1.322, released 10 November 2026, adds fast mode on Vertex in the global, US and EU regions. If Vertex refuses it, Claude Code falls back to standard speed.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work