Claude Code

Anthropic's agentic coding tool for terminal, IDEs, desktop, web, mobile and Slack that reads, edits and runs code.

Where it ranks

S
Coding
Coding agents · Cloud · 68 on Artificial Analysis Coding Agent Index (v1.5)

Ranked by its own benchmark result where it has one; otherwise by the best model it offers.

Vendor: Anthropic
Approach: Coding agents
Where it runs: Cloud only: needs the vendor’s service
Interface: Command line, IDE extension, Desktop app, Web app, Mobile app
Skill level: Intermediate: some setup or configuration
Price: From $20/mo
Pricing notes: Included in Claude Pro ($20/mo, or $17/mo billed annually), Max (from $100/mo), Team and Enterprise; not in the Free plan. Also usable pay-as-you-go with an API key.
Source code: Closed source
GitHub stars: 152.2k (18 Oct 2026)
Last verified: 18 Oct 2026

Price from claude.com, 18 Oct 2026.

Benchmark	Result	Entry on the leaderboard	As of	Source
Artificial Analysis Coding Agent Index (v1.5)	68	`Claude Code + Sonnet 5.5 (max)` AA label 'Claude Code - Sonnet 5.5 (max)'; Coding Agent Index v1.5, rank 1 of 42; components (pass@1 avg of 3 attempts): DeepSWE v1.1 72.0%; SWE-Atlas-QnA 66.9%; Terminal-Bench v4 66.2%; read from the page's embedded data; no last-updated date shown	18 Oct 2026	artificialanalysis.ai
Terminal-Bench 2.0	58%	`Claude Code + Claude Opus 4.6` rank 50 of 142 entries; raw accuracy 57.98 ± 2.9 (95% CI half-width); entry date 2026-02-05; marked verified; agent org: Anthropic; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai
Terminal-Bench 2.1	83.8%	`Claude Code + Fable 5` reasoning effort: xhigh; rank 6 of 22 entries; raw accuracy 83.82 ± 2.27 (95% CI half-width); entry date 2026-06-09; agent org: Anthropic; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai
Terminal-Bench 3.0	34%	`Claude Code + Fable 5` reasoning effort: max; rank 3 of 12 entries; raw accuracy 34.05 ± 3.35 (95% CI half-width); entry date 2026-07-13; agent org: Anthropic; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai
Terminal-Bench 4.0	64.8%	`Claude Code + Opus 5.5` reasoning effort: max; rank 1 of 35 entries; raw accuracy 64.85 ± 3.11 (95% CI half-width); entry date 2026-09-22; agent org: Anthropic; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai