GitHub Copilot (including Copilot CLI and cloud agent)
Cheapest paid coding agent at $10/month, CLI on the free plan; no independent test, and personal plans train by default.
Going away: Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra in GitHub Copilot (Opus 4.8 stays for individual annual plans), on 16 Nov 2026. What GitHub offers instead: Claude Opus 5.5, GPT-6.1 Sol or GPT-6 Luna. Source: github.blog, read 19 Oct 2026.
Should you use it?
Pick it if
Anyone who wants a paid coding agent for the least money, or a free one to try in the terminal.
Best for: Anyone wanting a paid coding agent for the least money, or a free one to try (Coding agents Top 20)
Skip it if
You want the top-ranked model by default; Claude Code uses Opus 5.5, at $20/month. OpenAI's Codex is the closest non-Anthropic scorer s8.
You give up: Free users can't pick models, and Claude and Codex agents need Pro+ at $39
The short version
- What this is
- GitHub's AI coding assistant: code completion and chat in your editor, a terminal agent (Copilot CLI) and a cloud agent that turns an issue into a pull request.
- Why it matters
- It is the cheapest way into a paid coding agent, but nobody independent has tested it by name, and personal data trains by default.
- Free plan includes the CLI and agent mode; Pro at $10/month adds the cloud agent s1.
- Opt out of training at github.com/settings/copilot on Free, Pro and Pro+ s2.
- No score yet: the only fresh independent test covers PR review, not its coding agent s7.
Good at
Weak at
- Personal plans train on your interaction data unless you opt out s2.
- Fourth on Martian's independent code review benchmark at 60.9% F1, behind Cubic at 64.9%, The New Stack reports s7.
- Free users get models only through automatic selection, and GitHub doesn't name the default for CLI or cloud agent s4.
Our take
Copilot, Copilot CLI and the cloud agent are one subscription with different ways in, so we review them together. On price it is the clear low point: the free plan includes the CLI and agent mode, and Pro at $10/month adds a cloud agent that researches the repository, makes changes in a temporary cloud environment and returns a pull request s1 s5. Copilot first became generally available in June 2022 s6.
We haven't scored it. No independent test of its coding agent or CLI names Copilot, and the Artificial Analysis coding agent article doesn't include it s3. The one fresh outside result is for PR review: on Martian's code review benchmark, Copilot came fourth at 60.9% F1, behind Cubic at 64.9%, The New Stack reported on 6 Oct 2026 s7. GitHub also doesn't say which model the CLI or cloud agent uses by default s4. Since 24 Apr 2026, Free, Pro and Pro+ interaction data trains GitHub's models unless you opt out s2, so change that setting if it matters to you.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. Once an independent agent benchmark or a credible independent write-up tests Copilot's agent, CLI or cloud agent by name.
CodingAgents
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for coding, from our scores, then the ones we'd also look at. The same kind of product comes first.
- OpenCodeTop scoredCoding agent80FreeScores 80 in coding, first in our ranking; free. Side by side
- Claude CodeCoding agent70$20 a monthUses Opus 5.5 by default, top of arena.ai WebDev; $20/month. Side by side
- OpenAI Codex CloudCoding agentFirst look: Worth trying$20 a monthOpenAI's cloud agent, included if you already pay for ChatGPT Plus. Side by side
- CursorCoding agentFirst look: Worth trying$8 a monthA full AI code editor; Pro is $20/month. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 8
- s1GitHub Copilot plans
- s2GitHub Blog: Updates to GitHub Copilot interaction data usage policy (25 Mar 2026)
- s3Artificial Analysis: Cursor Composer 2.5 on the Coding Agent Index (20 May 2026)
- s4GitHub Docs: Supported AI models in Copilot
- s5GitHub Docs: About Copilot cloud agent
- s6GitHub Blog: GitHub Copilot is generally available to all developers (21 Jun 2022)
- s7The New Stack: Copilot tops GitHub's own AI code review benchmark. An independent one tells a different story (6 Oct 2026)
- s8Artificial Analysis: Claude Code vs Codex, Coding Agent Index v1.5
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 3 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look covering Copilot, Copilot CLI and Copilot cloud agent as one product.
- Added The New Stack's 6 Oct 2026 report: Copilot code review is fourth on Martian's independent benchmark. That tests PR review only, not writing or fixing code, so still a First look.
- Audit: skip line now names OpenAI's Codex, the closest non-Anthropic scorer on Artificial Analysis's coding-agent test, next to Claude Code.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.