Claude Code vs Cline
Rankings as of
Last updated
Short answer: pick Claude Code for this job: Repo-sized edits from the terminal. Pick Cline (formerly Claude Dev) for this job: An agent inside stock VS Code. Claude Code scores 8.3 and is #1 in Coding and CLI agents. Cline scores 7.6 and is #2 in Coding and CLI agents.
| Compared on | Claude Code | Cline |
|---|---|---|
| What it is | Anthropic's coding agent for the terminal and supported editors. | Open-source coding agent inside VS Code. Bring your own model. |
| StackPick job | Coding and CLI agents, #1 | Coding and CLI agents, #2 |
| Best for | Repo-sized edits from the terminal | An agent inside stock VS Code |
| Score | 8.3 | 7.6 |
| Ease / Power / Price / Fit | 8 / 9 / 6 / 9 | 7 / 7 / 9 / 8 |
| Pricing | Check siteIncluded with Claude plans and API usage. Current packaging and prices: check site. | FreeOpen source and free. Model usage is billed by your provider. Rates: check site. |
| Also known as | — | Claude Dev |
| Visit | Visit | Visit |
Where Claude Code fits
Claude Code is Anthropic's coding agent. It reads a repository, edits files, and runs commands from the terminal, with editor integrations alongside. It is the pick when you want a strong agent on the current checkout and you are fine living in the terminal for the session.
Best use cases
- Implementing a feature across several files
- Running tests and fixing what they report
- A CLI agent paired with Claude models
Listed strengths
- Works on the repo you already have, in the terminal you already use
- Command execution is part of the loop, not a copy-paste step
- A natural pair with the Anthropic API if the product also calls Claude
Trade-off: You review diffs in a terminal-first workflow Access comes through Claude plans or API usage. Current packaging: check site
Where Cline fits
Cline is an open-source coding agent for VS Code, originally known as Claude Dev. It plans a task, edits files, and runs commands in the editor, using an API key you supply. It is the pick when you want an agent in stock VS Code and you do not want a paid editor wrapper.
Best use cases
- Multi-file edits without leaving VS Code
- Bringing your own Anthropic, OpenAI, or local model key
- Watching each command the agent wants to run
Listed strengths
- Open source and free
- Stays in VS Code
- You approve commands, which makes the loop visible
Trade-off: Setup means API keys and a model choice You are still in VS Code, which some people are trying to leave
Published prices
Prices change. Check the vendor page before you buy. A usage-based or credit-based plan can cost more than the subscription price.
Claude Code
- Pro. $20 per person per month (Source · checked ) Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates. $200 per person per year (Source · checked ) Annual charge is $200 billed up front. The page also shows this as $17 a month. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates.
- Max. $100 per person per month (Source · checked ) Billed monthly. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates.
- Ultra. $200 per person per month (Source · checked ) Billed monthly. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates.
- Team Standard. $25 per person per month (Source · checked ) Per seat, for teams of 2 to 150. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates. $20 per person per month, billed annually (Source · checked ) Listed as $20 per seat a month when billed annually, for teams of 2 to 150. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates.
- Team Premium. $125 per person per month (Source · checked ) Per seat, for teams of 2 to 150. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates. $100 per person per month, billed annually (Source · checked ) Listed as $100 per seat a month when billed annually, for teams of 2 to 150. Claude Code is included and shares this plan's usage limits. Past a limit, usage credits are billed at API rates.
- Enterprise. $20 per person per month, billed annually (Source · checked ) Seat fee only: $20 per seat a month, billed annually, 20 seat minimum. Usage is billed at API rates on top.
Cline
- Open Source. $0 per month (Source · checked ) Free for individual developers. No seat fee. AI inference is usage-based, or you can bring your own API key.
- ClinePass. $9.99 per month (Source · checked ) Flat $9.99 a month. The docs say it offers 2 to 5 times the usage of the standard API rate on popular open coding models.
Where the score comes from
The 0.7 gap comes from ease (8 vs 7) and power (9 vs 7) and price (6 vs 9) and vibe-coder fit (9 vs 8). How scores work.
What changed recently
Claude Code 2.1.328
Released November 19, 2026. Auto mode is available for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and the Claude apps gateway. Interactive sessions with no permission mode start in it. Plan mode and Bash prompts for those models on third-party providers use and offer auto mode, as on newer models. disableAutoMode turns both off. mcp_tool hooks can set onFailure to block, so a hook whose call fails blocks the action, as command and HTTP hooks already can. A warning says when a message from a session that skips permission prompts may be held and dropped by a cloud session. /status and claude doctor note when an OpenTelemetry exporter has no endpoint and its data would likely be lost. CLAUDE_CODE_DISABLE_DEFERRED_TOOL_RESUME lets a host stop claude -p --resume and --continue from running a tool call that a hook deferred. Apps that embed Claude Code can switch on the policy plugin's allowManagedModsOnly option. An admin's managed settings still win. The Claude apps gateway warns at startup when a policy's maxEffortLevel is not a valid effort level. /code-review on most models reports only bugs and CLAUDE.md violations. Run /simplify for reuse, simplification, and efficiency cleanups. Findings are marked Important, Pre-existing, or Nit, and each summary ends with a suggested fix. A clean review's list reads "Code review found no issues." Code Mode no longer runs UserPromptSubmit hooks, managed ones included, on scripts' output. To redact that output, use a PostToolUse hook with updatedToolOutput. /bug asks Yes or No before sending. deniedMcpServers entries of the form claude.ai <name> apply to that connector in cloud and self-hosted runner sessions too. Managed PostToolUse hooks no longer fire for calls refused before they ran. The release also includes a large fix sweep for permissions, Code Mode, MCP, Remote Control, cloud sessions, the self-hosted runner, VS Code, and the terminal UI.
Source for Claude Code 2.1.328 (opens in a new tab)Claude Code 2.1.327
Released November 17, 2026. /install-github-app asks before it changes a repository. claude mcp add-json - reads the server JSON from stdin so a token can stay off the command line, and that form is not available inside a Claude Code session. A resumed session says when earlier messages cannot be loaded. /status lists broken agent, skill, command, and output style files, keybinding errors, an unavailable sandbox, ignored permission settings, and hook matchers that never match. /config notes when other settings override a row. Gateway hint headers include x-claude-code-managed-settings-checksum where managed settings set CLAUDE_CODE_GATEWAY_HINT_HEADERS=1. attributionProject names a session's billing group for Claude apps gateways that set admin.billing_group_tag. /tui classic is the name for the non-fullscreen renderer, and /tui default still works. In VS Code, Claude Code: Add to Chat on the Explorer right-click menu @-mentions the selected files and folders. ExitWorktree asks before removing a worktree that may hold unsaved work, and refuses when nobody can answer unless an allow rule, auto mode, or bypass permissions allows it. claude mcp add --scope project stops, instead of overwriting the file, when .mcp.json lists its servers at the top level with no mcpServers key. Path checks refuse some symbolic links, and some paths now ask for permission. permissions.blockReadsOutsideWorkingDirectories asks about more Bash commands in bypass and auto modes, denies some in auto mode, and refuses more Bash commands that name a path under a Read or Edit deny rule. Auto mode's notice says an upcoming release removes the billed classifier fallback, and auto mode ignores more allow rules that run any package, such as Bash(pnpm dlx *). Bash commands whose variables expand to very long text are denied. A subagent resumed by a sibling's message follows the session's permission settings. Code Mode no longer refuses to start when an installed mod hooks tool calls. A subagent launched without a model stays on the model it started on when resumed, including after /model. The first subagent on a model waits up to 1.5 seconds, or 10 seconds in claude -p, for that model's settings from Anthropic. A session's first Bash command can run shell start-up files before the command is approved. Set CLAUDE_CODE_DISABLE_SHELL_HEAD_START=1 to turn that off. The release also includes a large fix sweep for permissions, the sandbox, MCP, sessions, artifacts, Remote Control, cloud sessions, VS Code, and the terminal UI.
Source for Claude Code 2.1.327 (opens in a new tab)Claude Code 2.1.326
Released November 16, 2026. Code Mode can stay on while agent teams are enabled, and a session with teams on starts in Code Mode if you already turned it on. Startup warns when an --allowedTools, --disallowedTools, or --tools value has an entry that does not look like a complete rule. A message explains why MCP servers stop loading when an administrator adds managed-mcp.json during a session. /status adds a row when the provider, or an environment variable such as DISABLE_TELEMETRY, turns features off. /plugin and claude plugin list note when a malformed plugin.json field such as author or homepage is ignored. Ctrl+O shows hidden startup notices, the empty prompt hints at what to do after a failed request, and a subagent view shows an esc to stop hint where Esc would stop it. OTEL_RESOURCE_INCLUDE_HOST, off by default, adds host.name and host.id to OpenTelemetry resource attributes. Background sessions that lost the LLM gateway the shell exported stop before any model request. The background service no longer ends your own processes, such as an SSH login, when a process number on its list was reused. Rules added in /permissions or at a tool prompt, and /add-dir folders, warn and name the settings file when it could not be written, instead of looking saved. The subagent model set in managed settings now applies in Claude Desktop's Code tab. Compaction on Bedrock, Vertex, and Foundry, and with telemetry off, summarizes instead of sometimes replying to one of your messages. Image-heavy sessions on Vertex AI compact and retry instead of sticking on a 400 error about a 30 MB request limit. When max_tokens exceeds the model's limit, Claude Code retries with the maximum the Anthropic API reports. Auto mode no longer stays on its local classifier, which counts toward usage, because of a stale saved value. /model shows Default as the plan's default model, and choosing it switches back to that default. The release also includes a large fix sweep for permissions, the sandbox, MCP, sessions, Remote Control, sign-in, and the terminal UI.
Source for Claude Code 2.1.326 (opens in a new tab)Claude Code 2.1.325
Released November 13, 2026. Sandboxed Bash commands follow the normal permission flow by default. Set sandbox.autoAllowBashIfSandboxed to true to keep running them without prompts, including in the highest-ranking managed settings source when managed settings turn the sandbox on. Read-only git commands ask first in a repository that is not the project's or one you trusted. Name it with --add-dir, not the additionalDirectories setting, to run them without prompts. Scheduled tasks and /loop ask before running a skill that declares allowed-tools or hooks. Add Skill(name) to permissions.allow to run it unattended. In Desktop, IDE, and SDK hosts, Always allow offers a saved rule on its own only when saving it would allow that command again, so a scheduled task that relied on one can now wait for you. The sandbox refuses sandboxed writes to .claude settings, skills, agents, commands, and hooks in added directories, as it does in the launch folder. An isolated worktree session or agent is refused git bisect run, git maintenance register and start, and scalar's set-up commands. EnterWorktree refuses a WorktreeCreate hook path that goes through a symlink inside the project. Plugin MCP bundles unpack under the plugins directory, not .mcpb-cache in the plugin's folder, so a read-only plugin folder can load. Programs the sandbox starts for its own use, such as its network bridge, run without Claude Code's sign-in tokens and API keys. Ripgrep, local git commands, and the sandbox runtime's helper programs run without the mTLS client key's passphrase. A security issue in how zstd-compressed responses are decoded is fixed. When an organization's policy blocks a request, the error says how to continue: run /rewind and change the message, or run /clear. In VS Code and similar integrated terminals, a spinner tip about re-running a notebook cell appears once Claude has read or edited a Jupyter notebook. VS Code shows prompt suggestions wherever the terminal shows them: Tab accepts the suggested next prompt, and promptSuggestionEnabled set to false in settings.json turns them off. VS Code adds a Console sign-in that creates no API key, and a field to paste the redirect URL when signing in to an MCP server from the panel in SSH, WSL, and container windows. CLAUDE_CODE_MAX_CONTEXT_TOKENS also sets the context window of unrecognized model IDs that start with claude-, such as a gateway's claude-sonnet-latest. The release also includes a large fix sweep for permissions, the sandbox, MCP, sessions, plugins, VS Code, and the terminal UI.
Source for Claude Code 2.1.325 (opens in a new tab)Claude Code 2.1.323
Released November 12, 2026. Code Mode is an experimental opt-in in which Claude writes JavaScript to call its tools. The Code Mode docs describe how to turn it on, or turn it off for an organization. plugin.json can set engines["claude-code"]. Plugins outside that Claude Code version range are not installed, updated, or loaded, and install and update pick the newest version that fits. claude plugin validate type-checks a plugin's TypeScript hooks module. Each finding is a warning, and --strict fails on it. It also reports the $ nouns a mod's engine.create hook adds, withholds, or replaces. When a model needs usage credits that are turned off or used up, a menu offers stop, switch to usage credits, or upgrade. Hooks that run long in claude -p and SDK sessions send a progress heartbeat every 30 seconds, so a host such as Claude Desktop will not end the turn as hung once that host includes this version. Artifact uploads accept .docx files. CLAUDE_CODE_AUTO_MODE_MODEL can be set in managed settings for Claude Desktop sessions on third-party providers, once Claude Desktop includes this version. A model ID Claude Code does not recognize is assumed to have a 1M-token context window, up from 200K. Set CLAUDE_CODE_DISABLE_1M_CONTEXT=1 to keep 200K. Sessions on other vendors' models with a smaller window can fail every turn once full, until /clear. MCP_SDK_GENERATION=v1 now runs the v2 MCP client in a compatibility mode, because the v1 MCP client is removed. /security-review asks before Claude runs it, and skills' inline git commands stop in bare-repository worktrees and similar folders until you allow them, outside auto mode and bypass. Sessions on the same machine can send each other about 100,000 messages without a prompt, up from about 20. The Bash sandbox on macOS, Linux, and WSL ignores write access granted through a symlink in a writable folder that leads elsewhere or to a missing path. On macOS and Linux, git worktree add, move, and remove fail read-only, as do commits in a worktree the session was not started in or given. An allow rule that looks like it holds a secret, or would be saved to a settings.local.json that git tracks, lasts for the session only. The subagentStatusLine setting is removed. A plugin's agent setting is deprecated: it still applies, and now warns at startup, in claude plugin list, and in claude plugin validate. On an on-demand self-hosted runner, a superseded work order exits 1 again. Versions 2.1.321 and 2.1.322 had changed that exit code to 0. VS Code asks you to trust a folder before the first session there. Declining leaves that folder's settings and MCP servers unused. The live output of a running Bash or PowerShell command appears in the chat, under the command's card. Claude Tag sessions started in Slack are on the Compliance API for Enterprise plans, in beta. The release also includes a large fix sweep for permissions, the sandbox, MCP, sessions, Remote Control, cloud sessions, VS Code, and the terminal UI.
Source for Claude Code 2.1.323 (opens in a new tab)
Alternatives
Codex CLI (7.5), Aider (7.4), Gemini CLI (7.2).
FAQ
- Should I pick Claude Code or Cline (formerly Claude Dev)?
- Pick Claude Code for this job: Repo-sized edits from the terminal. Pick Cline (formerly Claude Dev) for this job: An agent inside stock VS Code. Claude Code scores 8.3 and is #1 in Coding and CLI agents. Cline (formerly Claude Dev) scores 7.6 and is #2 in Coding and CLI agents.
- What do Claude Code and Cline (formerly Claude Dev) cost?
- Claude Code: Included with Claude plans and API usage. Current packaging and prices: check site. Cline (formerly Claude Dev): Open source and free. Model usage is billed by your provider. Rates: check site.
- Are these scores benchmarks?
- Initial editorial estimate. Not a measured benchmark. Price means value for an indie budget, not the sticker price.
- Do affiliate links change Claude Code or Cline (formerly Claude Dev)’s rank?
- Affiliate links may be used to monetize, but they never affect scores or rankings, and rankings are never sponsored.
Initial editorial estimate. Not a measured benchmark. Prices: check each vendor’s site. How scores work.
Some links may earn us a commission. It never changes scores or order.
Newsletter
Get this comparison when the scores move
Claude Code vs Cline. One email when rankings change or one of these tools ships something that matters. No spam, unsubscribe anytime.