Comparisons with published methodology Every claim dated & sourced

News · 2026-10-30

GitHub ships Copilot Fusion model orchestration and code review Max; Octoverse puts agents on 40% of pull requests

At GitHub Universe on 28 October 2026, GitHub made Copilot Fusion generally available: instead of picking a model per task, Fusion routes and orchestrates models behind one picker across three effort levels (Standard, High, Max). GitHub reports Fusion Max scored 60 on the Artificial Analysis Coding Agent Index, within two points of Claude Code running Opus 5.5 Max, at about half the average API cost per task, roughly half the tokens, and about 40% less time; users on paid plans get a limited-time 30% discount on model costs through Fusion, which bills each underlying model at its standard rate. Fusion is available on all Copilot plans in VS Code, the Copilot app, Copilot CLI and JetBrains IDEs, with an experimental preview of routing to supported local models. GitHub also introduced Copilot code review Max, which it says posted the highest F1 score on ReviewBench for high-severity issues, and Agent Merge, which watches a pull request and fixes failing workflows or merge conflicts in the cloud. The same day, Octoverse 2026 reported that more than 40% of pull requests on GitHub started with an agent's first draft in September, up from 17% in March (110 million in September alone, about 6x March's volume); agent-started pull requests merged within two weeks at 90% versus about 86% for the rest; 55% of Copilot's monthly active users now use agentic features, up from 35% a year earlier; and cloud-agent use grew 230% year over year.

What it means for buyers

Model choice is moving from a per-task human decision to a purchased routing layer: Copilot Fusion prices every model it picks at list rate under one subscription, which makes the real comparison for buyers not model-vs-model but platform-vs-platform overhead — directly the value math in our ai-coding-assistants comparison. The ReviewBench-topping code review Max turns GitHub into a first-party competitor for the dedicated reviewers in our agentic-code-review comparison, and Octoverse's 40%-of-pull-requests agent share is the clearest single datum yet that review, not generation, is where teams now spend their attention — the review tools' home turf. Note the numbers are GitHub's own, from GitHub's own benchmarks and telemetry.

Where to check it

Sources

  1. GitHub Universe 2026: Evolving every layer of the stack (GitHub Blog) — keynote post: Fusion results, code review Max ReviewBench claim, 28 October 2026, checked 2026-10-30
  2. Route and orchestrate models with GitHub Copilot Fusion (GitHub Changelog) — GA announcement: effort levels, per-model billing, 30% discount, client availability, local-model routing preview, checked 2026-10-30
  3. Octoverse 2026: commits and pushes reach new highs as developers build with agents (GitHub Blog) — annual report: agent-started PR share, merge rates, agentic-feature adoption, methodology and window, checked 2026-10-30