{
  "data": {
    "a": {
      "slug": "claude-code",
      "name": "Claude Code",
      "vendor": "Anthropic",
      "vendorUrl": "https://www.anthropic.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Anthropic's coding agent as a terminal program, also in VS Code, JetBrains, the desktop app and Anthropic-hosted cloud sessions.",
      "url": "https://www.anchorterminal.com/tools/claude-code",
      "markdownUrl": "https://www.anchorterminal.com/tools/claude-code.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/claude-code.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/claude-code.json",
      "repo": "https://github.com/anthropics/claude-code",
      "license": "Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source",
      "transports": [],
      "packages": [
        {
          "registry": "npm",
          "name": "@anthropic-ai/claude-code"
        }
      ],
      "auth": "mixed",
      "authNotes": "Sign in through the browser with a Pro, Max, Team or Enterprise claude.ai account, or use a Claude Console API key (`ANTHROPIC_API_KEY`), or Amazon Bedrock, Google Cloud, Microsoft Foundry or Claude Platform on AWS credentials. The free claude.ai plan doesn't include Claude Code.",
      "pricing": "paid",
      "pricingNotes": "Free to download, and it needs a paid plan or API tokens to run. Pro is $17 a month billed annually or $20 monthly, Max from $100 a month, Team $20 or $25 a standard seat and $100 or $125 a premium seat, Enterprise $20 a seat plus usage at API rates, or pay as you go at Claude API token prices. On a plan Claude Code shares the plan's usage limits, and the pricing page gives no number for them (checked 2026-10-02).",
      "priceSummary": "$20 / mo",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs or the pricing page (checked 2026-10-02).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 141000,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-02"
      },
      "docsUrl": "https://code.claude.com/docs/en/overview",
      "llmsTxt": "https://code.claude.com/docs/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "official",
        "harness",
        "coding-agent",
        "cli",
        "closed-source",
        "claude-only",
        "mcp",
        "llms-txt",
        "telemetry-default-on",
        "status-page",
        "card-required"
      ],
      "lastRelease": "2026-10-01",
      "graded": true,
      "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.",
      "anchor": {
        "graded": true,
        "score": 62.2,
        "grade": "B",
        "agentReady": false,
        "rank": 222,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 6,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 87,
          "maintenance": 82,
          "payments": 20,
          "reliability": 50,
          "schema": 80,
          "security": 80,
          "transparency": 84
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": -6,
        "negativeNotes": [
          "2025-10-03 to 2026-06-25. 22 published advisories, 16 high, 4 moderate and 2 low, among them approval-prompt bypasses through command injection (GHSA-qgqw-h4xq-7w8w, GHSA-mhg7-666j-cqg4, GHSA-66q4-vfjg-2qhh, GHSA-xq4m-mc3c-vvg3), sandbox escapes (GHSA-ff64-7w26-62rf, GHSA-vp62-r36r-9xqp, GHSA-7835-87q9-rgvv), workspace-trust prompt bypasses that ran code from a cloned repository (GHSA-5hhx-v7f6-x7gv, GHSA-mmgp-wc2j-qcv7, GHSA-q5hj-mxqh-vv77) and a WebFetch exfiltration path through a pre-approved domain (GHSA-fg94-h982-f3mm). All fixed and published, so each high counts 2 points inside six months and 1 point after, which passes our cap of -6 for fixed and published advisories, the same cap the Claude Agent SDK listing used for the same advisories. None published since 25 June 2026 (https://github.com/anthropics/claude-code/security/advisories)"
        ],
        "verdict": "Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.",
        "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.",
        "strengths": [
          "Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode",
          "An OS sandbox (Seatbelt, bubblewrap) whose network proxy denies every host outside an allowlist that starts empty",
          "`claude -p` with json and stream-json output, `--max-turns`, `--max-budget-usd`, resume and fork, and Python and TypeScript SDKs for the same loop",
          "Signed apt, dnf and apk repositories, a GPG-signed checksum manifest and a stable channel that skips releases with major regressions",
          "Telemetry documented per provider and per service, each with its own opt-out"
        ],
        "weaknesses": [
          "The sandbox is off by default and native Windows has none",
          "Auto mode, a classifier rather than a person, has been the starting mode for interactive sessions on every plan since 28 September 2026",
          "22 security advisories in the year to 25 June 2026, 16 rated high",
          "Usage metrics on by default on the Claude API, and error reports on Pro and Max sign-ins",
          "Closed source, Claude models only, and no free plan includes it"
        ],
        "agentNotes": [
          "Pass `--permission-mode` on every `claude -p` run. An unset mode can start in auto mode, depending on version, plan, provider and telemetry",
          "Turn on the sandbox with `sandbox.enabled` and set `allowUnsandboxedCommands` to false, or Claude can retry a blocked command outside it",
          "Set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` on a Claude login to stop metrics and error reports in one go",
          "Set `autoUpdatesChannel` to stable or `DISABLE_AUTOUPDATER=1` in CI. Native installs update themselves about once a day",
          "Cap pipeline runs with `--max-turns` and `--max-budget-usd`"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 62.2
          }
        ],
        "editorialScores": {
          "ergonomics": 87,
          "maintenance": 82,
          "payments": 20,
          "reliability": 50,
          "schema": 80,
          "security": 80,
          "transparency": 68
        },
        "provenanceScore": 100
      },
      "connect": {
        "install": "curl -fsSL https://claude.ai/install.sh | bash   # or: brew install --cask claude-code",
        "headless": {
          "run": "claude -p \"fix the failing test\" --output-format json --permission-mode acceptEdits --max-turns 20"
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/claude-code"
      },
      "sameCompany": [
        "anthropic-api",
        "claude-agent-sdk"
      ],
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Pro plan",
          "unit": "month",
          "usd": 20,
          "note": "$17 a month billed annually"
        },
        {
          "item": "Max plan",
          "unit": "month",
          "usd": 100,
          "note": "lowest Max tier"
        }
      ],
      "provenance": {
        "legalEntity": "Anthropic, PBC",
        "domain": "claude.com",
        "domainRegistered": "1995-05-24",
        "domainNote": "claude.com was registered in 1995, long before Anthropic bought it. Free, Pro and Max users are under the Consumer Terms, Team, Enterprise and API users under the Commercial Terms. The security.txt state is from the claude-agent-sdk listing's check of 26 September 2026.",
        "endpointOnVendorDomain": null,
        "terms": "https://www.anthropic.com/legal/commercial-terms",
        "privacy": "https://www.anthropic.com/legal/privacy",
        "statusPage": "https://status.claude.com",
        "changelog": "https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md",
        "securityTxt": "valid",
        "checked": "2026-10-01",
        "score": 100
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/claude-code.json",
      "live": {
        "slug": "claude-code",
        "vendorStatus": {
          "page": "https://status.claude.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-04T22:02:07.748562687Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "anthropics/claude-code",
            "version": "v2.1.289",
            "released": "2026-10-03",
            "seenAt": "2026-10-04T16:23:40.938881062Z"
          },
          {
            "registry": "npm",
            "name": "@anthropic-ai/claude-code",
            "version": "2.1.289",
            "seenAt": "2026-10-04T16:23:40.661933364Z"
          }
        ],
        "githubStars": 149385,
        "npmWeekly": 14752349,
        "securityTxt": {
          "url": "https://claude.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:15:52.669899519Z"
        },
        "llmsTxt": {
          "url": "https://code.claude.com/docs/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:17:26.148616011Z"
        },
        "domain": {
          "domain": "claude.com",
          "registered": "1995-05-24",
          "source": "https://rdap.verisign.com/com/v1/domain/claude.com",
          "checkedAt": "2026-10-04T13:04:27.501644209Z"
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-10-04T15:47:25.207817173Z",
            "changedAt": "2026-10-04T15:47:25.207817173Z",
            "fingerprint": "9c0f09978f55"
          }
        ],
        "updatedAt": "2026-10-04T22:02:07.748562687Z"
      }
    },
    "b": {
      "slug": "gemini-cli",
      "name": "Gemini CLI",
      "vendor": "Google",
      "vendorUrl": "https://geminicli.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Google's open-source coding agent for the terminal, in TypeScript on Node 20 or newer.",
      "url": "https://www.anchorterminal.com/tools/gemini-cli",
      "markdownUrl": "https://www.anchorterminal.com/tools/gemini-cli.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-cli.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-cli.json",
      "repo": "https://github.com/google-gemini/gemini-cli",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [
        {
          "registry": "npm",
          "name": "@google/gemini-cli"
        }
      ],
      "auth": "mixed",
      "authNotes": "Sign in with a Google account (Gemini Code Assist for individuals, Google AI Pro or Ultra, Code Assist Standard or Enterprise), or use a Gemini API key from AI Studio or Vertex AI credentials. Google's terms forbid using the Gemini CLI sign-in from third-party software.",
      "pricing": "freemium",
      "pricingNotes": "Free with a Google sign-in, up to 1,000 model requests a user a day, or 250 a day on Flash with an unpaid Gemini API key. Google AI Pro raises the daily limit to 1,500 and Ultra to 2,000, Code Assist Standard to 1,500 and Enterprise to 2,000. Pay as you go through a paid Gemini API key or Vertex AI at token rates. Requests are also limited per minute (checked 2026-10-02).",
      "priceSummary": "Freemium",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-02).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 107000,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-02"
      },
      "docsUrl": "https://geminicli.com/docs/",
      "llmsTxt": "https://geminicli.com/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "official",
        "harness",
        "coding-agent",
        "cli",
        "open-source",
        "typescript",
        "mcp",
        "llms-txt",
        "telemetry-default-on",
        "pre-1.0",
        "free-tier",
        "no-card",
        "gemini-only"
      ],
      "lastRelease": "2026-09-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 72.3,
        "grade": "BB",
        "agentReady": true,
        "rank": 72,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 3,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 78,
          "maintenance": 88,
          "payments": 40,
          "reliability": 71,
          "schema": 93,
          "security": 67,
          "transparency": 90
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": -2,
        "negativeNotes": [
          "2026-04-24. GHSA-wpqr-6v78-jr5g, critical (CVSS 10). In CI, headless Gemini CLI trusted the workspace folder automatically and loaded its configuration, and `--yolo` ignored fine-grained tool allowlists, so a workflow fed untrusted pull requests or issues could run an attacker's code. Fixed in @google/gemini-cli 0.39.1 and run-gemini-cli 0.1.22 and published, so the deduction is small (https://github.com/advisories/GHSA-wpqr-6v78-jr5g)"
        ],
        "verdict": "Apache-2.0, CI passing on main, and 583 open issues with priority labels. Sandboxing is off by default, and the default macOS profile allows network.",
        "strengths": [
          "Apache-2.0, CI passing on main, and 583 open issues with priority labels",
          "A weekly stable release after a week in preview, under a written release policy",
          "Headless JSON and stream-json output with documented exit codes, including 53 for the turn limit",
          "A TOML policy engine with admin policy paths, folder trust on by default and a setting that blocks yolo mode",
          "1,000 free requests a day with a Google sign-in and no card"
        ],
        "weaknesses": [
          "Sandboxing is off by default, and the default macOS profile allows network",
          "Usage statistics on by default, and the free tier may train on data unless the user opts out",
          "A critical advisory in April 2026 (CVSS 10) for CI runs that trusted untrusted repositories",
          "Pre-1.0 at 0.62.0, and Gemini models only",
          "Open P1 report #29310 says yolo and auto_edit auto-allow obfuscated shell commands"
        ],
        "agentNotes": [
          "Set `GEMINI_TRUST_WORKSPACE` to true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own",
          "Turn on the sandbox with `-s` or `tools.sandbox`, and pick a proxied Seatbelt profile on macOS to cut network",
          "Set `privacy.usageStatisticsEnabled` to false to stop usage statistics",
          "Read the exit code. 42 is bad input and 53 is the turn limit",
          "Use `--output-format stream-json` to get tool calls and results as JSONL events"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 72.3
          }
        ],
        "editorialScores": {
          "ergonomics": 78,
          "maintenance": 88,
          "payments": 40,
          "reliability": 71,
          "schema": 93,
          "security": 67,
          "transparency": 80
        },
        "provenanceScore": 100
      },
      "connect": {
        "install": "npm i -g @google/gemini-cli   # or: brew install gemini-cli",
        "headless": {
          "run": "gemini -p \"fix the failing test\" --output-format json --approval-mode auto_edit"
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/gemini-cli"
      },
      "sameCompany": [
        "gemini-api",
        "gemini-embedding",
        "vertex-ai-tuning",
        "google-model-armor",
        "google-imagen",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "google-adk",
        "google-secret-manager",
        "google-weather-api",
        "chrome-devtools-mcp",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "google-drive-api"
      ],
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "google.com",
        "domainRegistered": "1997-09-15",
        "endpointOnVendorDomain": null,
        "terms": "https://geminicli.com/docs/resources/tos-privacy",
        "privacy": "https://policies.google.com/privacy",
        "statusPage": "https://aistudio.google.com/status",
        "changelog": "https://geminicli.com/docs/changelogs",
        "securityTxt": "valid",
        "checked": "2026-10-01",
        "notes": [
          "The docs are on geminicli.com. The terms page there maps each sign-in method to its own terms and privacy notice (Gemini Code Assist, the Gemini API unpaid and paid services, Google Cloud).",
          "The status page is the Gemini API's. We found no status page for Gemini Code Assist sign-ins.",
          "Legal entity, domain date and security.txt for google.com are from the gemini-api listing's check of 26 September 2026."
        ],
        "score": 100
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-cli.json",
      "live": {
        "slug": "gemini-cli",
        "vendorStatus": {
          "page": "https://aistudio.google.com/status",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-10-04T21:40:04.477079675Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "google-gemini/gemini-cli",
            "version": "v0.62.0",
            "released": "2026-09-29",
            "seenAt": "2026-10-04T16:27:48.184399075Z"
          },
          {
            "registry": "npm",
            "name": "@google/gemini-cli",
            "version": "0.62.0",
            "seenAt": "2026-10-04T16:27:47.915925343Z"
          }
        ],
        "githubStars": 107231,
        "npmWeekly": 459071,
        "securityTxt": {
          "url": "https://google.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2030-04-01T00:00:00z",
          "checkedAt": "2026-10-04T15:15:53.387118101Z"
        },
        "llmsTxt": {
          "url": "https://geminicli.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:17:48.20670565Z"
        },
        "domain": {
          "domain": "google.com",
          "registered": "1997-09-15",
          "source": "https://rdap.verisign.com/com/v1/domain/google.com",
          "checkedAt": "2026-10-04T13:05:50.737985829Z"
        },
        "pages": [
          {
            "url": "https://geminicli.com/docs/changelogs",
            "kind": "changelog",
            "status": 304,
            "checkedAt": "2026-10-04T15:44:53.591365058Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "1a4924fbe02a"
          },
          {
            "url": "https://geminicli.com/docs/resources/tos-privacy",
            "kind": "terms",
            "status": 304,
            "checkedAt": "2026-10-04T15:44:55.657597873Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "f7d55fbc670d"
          }
        ],
        "updatedAt": "2026-10-04T21:40:04.477079675Z"
      }
    },
    "summary": "Gemini CLI has a score of 72.3 (BB) against Claude Code's 62.2 (B). Both do agent harness. The largest gap is reliability, 21 points."
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli",
    "json": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.md",
    "slim": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.min.md"
  },
  "markdown": "Gemini CLI has a score of 72.3 (BB) against Claude Code's 62.2 (B). Both do agent harness. The largest gap is reliability, 21 points.\n\n- Claude Code: grade B, 62.2/100, rank #222 of 452. Markdown https://www.anchorterminal.com/tools/claude-code.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-code.json\n- Gemini CLI: grade BB, 72.3/100, rank #72 of 452. Markdown https://www.anchorterminal.com/tools/gemini-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-cli.json\n\n## Which one, for what\n\nPick Claude Code for agent ergonomics (+9), security \u0026 auth (+13).\n\nPick Gemini CLI for reliability (+21), schema \u0026 documentation (+13), payments \u0026 pricing (+20), maintenance \u0026 community (+6), transparency \u0026 trust (+6).\n\n## Score by category\n\n| Category | Weight | Claude Code | Gemini CLI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 71 | Gemini CLI +21 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 93 | Gemini CLI +13 |\n| Agent ergonomics | 13% (16.2 this run) | 87 | 78 | Claude Code +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 80 | 67 | Claude Code +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 40 | Gemini CLI +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 88 | Gemini CLI +6 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 90 | Gemini CLI +6 |\n| Negative events | ≤15 | -6 | -2 | |\n| **Total** | | **62.2 · B** | **72.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Claude Code | Gemini CLI |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Anthropic | Google |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports |  |  |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Paid | Freemium |\n| x402 | no | no |\n| Licence | Proprietary. `LICENSE.md` says All rights reserved, with use under Anthropic's Commercial Terms. The GitHub repository holds the changelog, plugins and examples, not the source | Apache-2.0 |\n| Tools exposed | none | none |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | not listed |\n| Last release | 2026-10-01 | 2026-09-29 |\n| Popularity | 141k stars | 107k stars |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Claude Code.** Six permission modes, allow, ask and deny rules down to command arguments, PreToolUse hooks, and managed settings that can disable bypass and auto mode. The sandbox is off by default and native Windows has none.\n\n**Gemini CLI.** Apache-2.0, CI passing on main, and 583 open issues with priority labels. Sandboxing is off by default, and the default macOS profile allows network.\n\n## Before you call either\n\n### Claude Code\n\n1. Pass `--permission-mode` on every `claude -p` run. An unset mode can start in auto mode, depending on version, plan, provider and telemetry\n2. Turn on the sandbox with `sandbox.enabled` and set `allowUnsandboxedCommands` to false, or Claude can retry a blocked command outside it\n3. Set `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` on a Claude login to stop metrics and error reports in one go\n4. Set `autoUpdatesChannel` to stable or `DISABLE_AUTOUPDATER=1` in CI. Native installs update themselves about once a day\n5. Cap pipeline runs with `--max-turns` and `--max-budget-usd`\n\n### Gemini CLI\n\n1. Set `GEMINI_TRUST_WORKSPACE` to true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own\n2. Turn on the sandbox with `-s` or `tools.sandbox`, and pick a proxied Seatbelt profile on macOS to cut network\n3. Set `privacy.usageStatisticsEnabled` to false to stop usage statistics\n4. Read the exit code. 42 is bad input and 53 is the turn limit\n5. Use `--output-format stream-json` to get tool calls and results as JSONL events\n\n## Other comparisons with Claude Code or Gemini CLI\n\n- [Aider vs Claude Code](https://www.anchorterminal.com/compare/aider-vs-claude-code.md)\n- [Aider vs Gemini CLI](https://www.anchorterminal.com/compare/aider-vs-gemini-cli.md)\n- [Claude Code vs Cline](https://www.anchorterminal.com/compare/claude-code-vs-cline.md)\n- [Claude Code vs Cursor CLI](https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli.md)\n- [Claude Code vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/claude-code-vs-github-copilot-cli.md)\n- [Claude Code vs goose](https://www.anchorterminal.com/compare/claude-code-vs-goose.md)\n- [Claude Code vs OpenAI Codex](https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.md)\n- [Claude Code vs OpenCode](https://www.anchorterminal.com/compare/claude-code-vs-opencode.md)\n- [Claude Code vs OpenHands](https://www.anchorterminal.com/compare/claude-code-vs-openhands.md)\n- [Cline vs Gemini CLI](https://www.anchorterminal.com/compare/cline-vs-gemini-cli.md)\n- [Cursor CLI vs Gemini CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-gemini-cli.md)\n- [Gemini CLI vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-github-copilot-cli.md)\n- [Gemini CLI vs goose](https://www.anchorterminal.com/compare/gemini-cli-vs-goose.md)\n- [Gemini CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex.md)\n- [Gemini CLI vs OpenCode](https://www.anchorterminal.com/compare/gemini-cli-vs-opencode.md)\n- [Gemini CLI vs OpenHands](https://www.anchorterminal.com/compare/gemini-cli-vs-openhands.md)\n\n## Disclosure\n\n- Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Claude Code vs Gemini CLI",
        "url": ""
      }
    ],
    "description": "Gemini CLI has a score of 72.3 (BB) against Claude Code's 62.2 (B). Both do agent harness. The largest gap is reliability, 21 points. Category scores, facts, verdicts and agent notes side by side.",
    "facts": [
      "Claude Code B 62.2",
      "Gemini CLI BB 72.3",
      "scores"
    ],
    "h1": "Claude Code vs Gemini CLI",
    "image": "https://www.anchorterminal.com/assets/og/compare-claude-code-vs-gemini-cli.png",
    "path": "/compare/claude-code-vs-gemini-cli",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Claude Code vs Gemini CLI for AI agents, B 62.2 vs BB 72.3",
    "toc": null,
    "updated": "2026-10-04",
    "url": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli"
  },
  "tokens": {
    "markdown": 1650,
    "slim": 330
  },
  "version": 1
}