Verified August 18, 2026. Every price, limit, and benchmark below was checked against official docs and leaderboards on that date.
Originally published May 24, 2026.
People keep searching for this comparison, and most of what ranks is stale or vibes. The first version of this post was vibes too. This rewrite is numbers. One naming trap before we start: Codex here means OpenAI's current coding agent, not the retired 2021 model that once powered the original Copilot.
The 30-second version
| GitHub Copilot | OpenAI Codex | Claude Code | |
|---|---|---|---|
| What it is | Autocomplete, chat, and agents inside your editor and GitHub | OpenAI's coding agent inside ChatGPT, your terminal, and the cloud | Anthropic's agent-first coding tool, born in the terminal |
| Runs in | VS Code, Visual Studio, JetBrains, Xcode, Eclipse, github.com, CLI, mobile | ChatGPT desktop app, CLI, IDE extension, web, and via GitHub, Slack, Linear | Terminal, VS Code, JetBrains, desktop app, web, mobile |
| Models | 20+ model picker across OpenAI, Anthropic, Google, Microsoft, xAI, Moonshot | GPT-5.6 family, plus GPT-5.5 and GPT-5.4 until they retire Aug 31, 2026 | Sonnet 5, Opus 5, Fable 5, Haiku 4.5 |
| Cheapest way in | Free tier, then Pro at $10 | ChatGPT Go at $8 | Free tier, then Pro at $20 |
| Persona | The neighbor next door | The road-trip uncle | The short-errand guy who became a general contractor |
Pricing
| Tier | GitHub Copilot | OpenAI Codex (ChatGPT) | Claude Code (Claude) |
|---|---|---|---|
| Free | $0, 2,000 completions, limited chat on auto model selection | $0, basic Codex access | $0, tight standard limits |
| Entry | Pro $10 ($15 in AI Credits included) | Go $8, light usage | Pro $20, or $17 billed annually |
| Mid | Pro+ $39 ($70 in credits) | Plus $20 | Same Pro $20 covers it |
| Heavy | Max $100 ($200 in credits) | Pro $100 (5x Plus) or $200 (20x) | Max $100 (5x Pro) or $200 (20x) |
| Team seat | Business $19 | Business $20 annual, $25 monthly | Team $25, or $20 annual; premium seat $125, or $100 annual |
| Enterprise seat | Enterprise $39 | Custom | $20 self-serve, or custom |
| Pay as you go | Extra credits at $0.01 each | API key at token rates, or extra credits | Claude API at token rates |
All three repriced in the first half of 2026, and in the same direction: flat subscriptions with a metered engine underneath. Copilot swapped premium requests for AI Credits on June 1. Codex moved to token-based credits on April 2, and ChatGPT added the $100 Pro tier on April 9. Anthropic doubled Claude Code's five-hour caps on May 6. Whichever you pick, you are budgeting tokens now, not seats.
Usage limits
| GitHub Copilot | OpenAI Codex | Claude Code | |
|---|---|---|---|
| Meter | AI Credits, 1 credit = $0.01, billed on tokens | Credits per token, varies by model | Time: rolling 5-hour window plus a weekly cap |
| What you get | $15/mo Pro, $70 Pro+, $200 Max; Business 1,900 credits, Enterprise 3,900 (promo 3,000 and 7,000 until Sep 1, 2026) | On Plus, per 5-hour window: 10 to 100 messages on GPT-5.6 Sol, 25 to 200 on Terra, 250 to 2,000 on Luna; Pro is 5x or 20x that | Pro roughly 40 to 80 hours of Sonnet a week; Max 5x roughly 140 to 280; Max 20x roughly 240 to 480 |
| Never metered | Autocomplete and next-edit suggestions on all paid plans | Nothing | Nothing |
| When you run out | Buy credits or wait for the month | Buy credits, wait, or switch to an API key | Wait for the reset, or run through the API |
| Fine print | Cloud agent also consumes Actions minutes | Local and cloud tasks share one pool; weekly caps can apply on top | Claude chat and Claude Code share the same pool |
Models
| GitHub Copilot | OpenAI Codex | Claude Code | |
|---|---|---|---|
| Native lineup | No frontier model of its own; Raptor mini (tuned GPT-5 mini) plus Microsoft's MAI-Code-1-Flash and MAI-Code-1.1-Flash | GPT-5.6 Sol, Terra, and Luna (272K context), plus GPT-5.3-Codex-Spark in research preview; GPT-5.5 and GPT-5.4 retire Aug 31, 2026 | Sonnet 5 (default, native 1M context), Opus 5 with optional 2.5x fast mode, Fable 5, Haiku 4.5 |
| Other vendors | The whole market: GPT-5.x including Codex variants, Claude from Haiku 4.5 up to Opus 5 and Fable 5, Gemini 3.1 Pro to 3.7 Flash, Grok 4.5 and 4.6, Kimi K2.7 Code | No | No |
| Catches | Free and Student tiers get automatic model selection only; Claude Fable 5 needs business or enterprise enablement | Codex-Spark is Pro-only for now | Fable 5 is opt-in via /model fable and unavailable under zero-data-retention agreements |
Agents and automation
| Capability | GitHub Copilot | OpenAI Codex | Claude Code |
|---|---|---|---|
| Inline autocomplete | Yes, unlimited on paid plans | No | No |
| IDE chat and agent mode | Yes | Yes, via extension | Yes, VS Code and JetBrains |
| CLI agent | Copilot CLI, all tiers | Codex CLI, open source | The original surface, fully scriptable |
| Cloud agent | Assign an issue, get a PR; 59-minute sessions, GitHub repos only | Parallel cloud tasks, kicked off from web, GitHub, Slack, or Linear | Web and mobile sessions you can pull into your terminal |
| Parallel work | One branch and PR per task | Several cloud tasks at once | Subagents and agent teams inside one session |
| Code review | Agentic PR review that can hand fixes straight to the agent | PR review inside the ChatGPT desktop app since July 9 | /review locally, GitHub Action for every PR |
| MCP support | Yes, all tiers | Yes | Yes, Anthropic wrote the spec |
| Customization | Custom instructions, Memory on paid tiers | AGENTS.md | CLAUDE.md, hooks, skills, subagents, Agent SDK |
| Scheduled runs | Not offered | Not offered | Routines and desktop scheduled tasks |
| Hires the competition | Pro+ and Max can delegate tasks to Claude and Codex agents (preview) | No | No |
The personas from the first version of this post survived the data pass. Copilot is still the neighbor who knows the block, closest to your editor and your repo host. Codex is still the road-trip uncle: hand over the keys, check back later. Claude Code outgrew short errands; with subagents, hooks, and scheduled routines it is now the most customizable of the three. That part is opinion. The tables are not.
Benchmarks
| Benchmark | Best relevant results, August 2026 | What it measures |
|---|---|---|
| Terminal-Bench 2.1, official leaderboard | Claude Code with Fable 5 leads at 83.8%, Codex with GPT-5.5 next at 83.1%; then Claude Code with Opus 4.8 at 78.9% and Codex with GPT-5.6 Terra at 78.4% | Agents doing real work in a terminal |
| SWE-bench Verified, vendor-reported | Claude Opus 4.8 at 88.6% | Fixing real GitHub issues |
| SWE-bench Pro, vendor-reported | Opus 4.8 at 69.2% vs GPT-5.5 at 58.6% | A harder, contamination-resistant variant |
| GitHub Copilot | No product-level entry on either board; its ceiling is whichever model you pick | n/a |
Hold the scores loosely. Vendor numbers come from tuned harnesses, the official leaderboard still lags one release (Opus 5 is not on it yet), and the top two entries sit 0.7 points apart. The first version of this post argued you cannot benchmark a feeling. The data version of that claim: the harness you actually enjoy using matters more than two benchmark points.
Privacy and enterprise
| Question | GitHub Copilot | OpenAI Codex | Claude Code |
|---|---|---|---|
| Trains on your code? | Free, Pro, and Pro+ interaction data trains models by default, opt out in settings (a 2026 change); Business and Enterprise never | Consumer plans: opt out in data controls; Business and Enterprise: not by default | Consumer plans: your privacy setting decides; Team, Enterprise, and API: no |
| IP indemnity | Business and Enterprise; individual tiers explicitly not included | Copyright Shield, on Enterprise and the API | Included in Anthropic's commercial terms |
| Admin controls | Org-wide policies, audit logs, content exclusions, usage analytics | Workspace controls; SSO and compliance API on Enterprise | Console roles, spend caps, managed settings, zero data retention on request |
| Worth knowing | Self-serve Business signup is paused for GitHub Free and Team orgs since April 22, 2026 | Pricing changed twice this spring; recheck the rate card before budgeting | Fable 5 does not run under zero-data-retention agreements |
Which one, then
| If you | Pick |
|---|---|
| Live in your editor and want the cheapest useful upgrade | Copilot Pro at $10 |
| Already pay for ChatGPT | Codex, it is in your plan |
| Want fire-and-forget tasks from Slack or Linear | Codex |
| Want the deepest customization: hooks, subagents, MCP, an SDK | Claude Code |
| Need one bill and GitHub-native admin for a team | Copilot Business |
| Are a founder validating an idea, not shipping a platform | A $20 tier and a throwaway prototype, not a $200 tier |
| Are not sure you should be writing the code at all | Vibe-code or hire, then a $20 tier |
My honest answer in 2026 is two of them. Autocomplete and delegation are different jobs, and the vendors have stopped pretending otherwise: Copilot Pro+ can now hand tasks to Claude and Codex agents from inside GitHub. Keep Copilot for in-editor flow, add Codex or Claude Code for delegated work, and start from whichever subscription you already pay.
Narrowing it to two tools? I have head-to-heads on Claude Code vs Cursor and Cursor vs GitHub Copilot. Swapping Copilot for Cursor in this three-way? Read Codex vs Cursor vs Claude Code. Want the terminal-only version of this question, with Gemini CLI in the mix? Read Gemini CLI vs Claude Code vs Codex. Prefer an open source agent that is not tied to one model vendor? OpenCode vs Claude Code vs Codex covers that. Need an agent for work that is not code at all? Claude Cowork vs Claude Code vs OpenClaw covers that side, and Hermes vs OpenClaw vs Claude Code compares the two self-hosted assistants directly. Comparing editors rather than agents? Windsurf vs Cursor vs Claude Code covers that side, including the Windsurf rename, and Antigravity vs Cursor vs Claude Code covers Google's free entrant. For where AI actually earns its keep, see my enterprise AI reality check.
