specs at a glance

Leaderboard rank#3 of 10
SWE-bench Verified85.2%
SWE-bench Pro63.2%
Terminal-Bench80.4% (TB2.1)
Input price / 1M$2
Output price / 1M$10
Context window1M
Open weightsNo
AccessAPI · Claude Code · claude.ai (Free/Pro default)
MakerAnthropic

how good is Claude Sonnet 5 at coding?

Claude Sonnet 5 sits at #3 of 10 ranked models, posting 85.2% on SWE-bench Verified — 9.8 points behind #1 Claude Fable 5. On the harder SWE-bench Pro it scores 63.2%. Terminal-Bench (agentic terminal work): 80.4% (TB2.1).

Score provenance: Anthropic-reported. Intro pricing $2/$10 per 1M through Aug 31, 2026, then $3/$15.

what does Claude Sonnet 5 cost?

$2 per 1M input tokens and $10 per 1M output — #6 cheapest of the 10 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.

where can you use it?

Available via API · Claude Code · claude.ai (Free/Pro default). As a proprietary model, you're on the maker's infrastructure and release schedule.

head-to-head

Full storyClaude Sonnet 5: Near-Opus Coding at Half the Price

Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-04.