OpenCode
Free open-source coding agent for 75+ model providers; scored 54 with GLM-5.3. Skip it for one flat monthly plan.
Should you use it?
Pick it if
Developers who want a free, open agent in the terminal, desktop or editor and want to choose their own model.
Best for: Developers who want a free agent and the choice of 75+ model providers (Coding agents Top 20)
Skip it if
You want one flat monthly price with a strong model included; Claude Code, Codex CLI with ChatGPT Plus, or GitHub Copilot do that.
You give up: Scores below Codex and Claude Code; several free Zen models may train on prompts
The short version
- What this is
- An open-source AI coding agent for the terminal, a desktop app and editor extensions that works with almost any model provider.
- Why it matters
- It is one of the most used open coding agents and costs nothing beyond the model, which can be one you already pay for.
- Free and MIT licensed (212.6k GitHub stars); works with 75+ providers, local models, and Copilot or ChatGPT logins s1 s2.
- Scores 80 for coding: free and maintained; Artificial Analysis rates it 54 with GLM-5.3 at $4.24 a task s5.
- Check a free Zen model's data policy before using it on private code s3.
Good at
Our take
OpenCode is a free, MIT-licensed coding agent that runs in the terminal, as a desktop app or in your editor s1 s2. Like Cline, it is as good as the model you plug in. It connects to 75+ providers and local models, and it can sign in with a GitHub Copilot or ChatGPT Plus or Pro account, so you may not need a new subscription s1.
Artificial Analysis's Coding Agent Index v1.5 comparison page scores OpenCode with GLM-5.3 at 54 for $4.24 a task, against 66 for Claude Code with Opus 5.5 (max) s5. Version 1.5 has been in use since September 2026 s6, so the result is current. The score is 80 because the tool is free and actively maintained s2 s4; the tested model, GLM-5.3, sits at rank 22 of 142 on arena.ai WebDev s7, and Artificial Analysis shows no OpenCode result with a stronger model. OpenCode says it does not store your code or context s1. Its optional Zen service lists free models, but most are free only for a limited time and several may use your prompts to improve the model s3, so pick a model with a clear policy for private code.
Score
A score from 0 to 100 per job, against everything available today. Overall 80 across 1 job, the average of the job scores.
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.
Our checklist score, going by an independent test, a public leaderboard and the maker’s pages.
Our checklist
2 sources
Sources and notes
Independent testPublic leaderboardMaker’s pagesChecklist 8/10: does the job 1 (Artificial Analysis Coding Agent Index v1.5, in use since September 2026 s6, scores it 54 with GLM-5.3 at $4.24 a task, the only model shown for it, against 63 to 68 for the best Codex and Claude Code rows s5); underlying quality 1 (GLM-5.3 (max) is arena.ai WebDev rank 22 of 142, glm-5.3-max s7); value 2 (free under MIT s2); privacy 2 (OpenCode says it stores none of your code or context s1); limits 2 (version 1.19.0 released 11 Oct 2026 s4).
Alternatives
Better or cheaper for coding, from our scores, then the ones we'd also look at. The same kind of product comes first.
- ClineCoding agentFirst look: Worth tryingFreeAnother free open-source agent, focused on VS Code and JetBrains. Side by side
- OpenAI Codex CLICoding agent70$20 a monthOpen-source terminal agent included with ChatGPT Plus. Side by side
- Claude CodeCoding agent70$20 a monthFlat-price agent on Claude's top coding models. Side by side
- Claude Opus 5.5BetterText model100$20 a monthScores 100 in coding, against 80 here; $20 a month. Side by side
Value for money
Where it sits in coding: higher is a better score, further left is cheaper. Green dots are the Best buys.
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
The coding score comes from our own checklist of the product.
Independent testPublic leaderboardMaker’s pages
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 7
- s1OpenCode home page
- s2GitHub: anomalyco/opencode
- s3OpenCode docs: Zen
- s4GitHub: OpenCode releases
- s5Artificial Analysis: Claude Code vs OpenCode, Coding Agent Index v1.5
- s6Artificial Analysis: Coding Agent Index v1.5 methodology
- s7arena.ai Code Arena: WebDev leaderboard
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 as a category leader among open coding agents. No independent test of OpenCode itself, so not rated. Released date is the latest version, 1.19.0; GitHub showed the day without a year.
- Added Artificial Analysis Coding Agent Index v1.5 score: 54 with GLM-5.3. No per-result date and the main index hides values, so still a First look.
- New: First look to ScoredNew: Coding ratedRated for coding by the checklist. Artificial Analysis's methodology page shows v1.5 has been in use since September 2026, so its score falls inside the 90-day window. Agents not rated yet.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.