specs at a glance

Leaderboard rank#2 of 10
SWE-bench Verified~86%
SWE-bench Pro69.2%
Terminal-Bench~82.7% (TB2.1)
Input price / 1M$5
Output price / 1M$25
Context window1M
Open weightsNo
AccessAPI · Claude Code · claude.ai (Max)
MakerAnthropic

how good is Claude Opus 4.8 at coding?

Claude Opus 4.8 sits at #2 of 10 ranked models, posting ~86% on SWE-bench Verified — 9 points behind #1 Claude Fable 5. On the harder SWE-bench Pro it scores 69.2%. Terminal-Bench (agentic terminal work): ~82.7% (TB2.1).

Score provenance: Anthropic-reported; independent evals (vals.ai) track within ~1 point.

what does Claude Opus 4.8 cost?

$5 per 1M input tokens and $25 per 1M output — #8 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 (Max). As a proprietary model, you're on the maker's infrastructure and release schedule.

head-to-head

Primary source

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