specs at a glance
| Leaderboard rank | #3 of 13 |
|---|---|
| SWE-bench Verified | 88.6% |
| SWE-bench Pro | 69.2% |
| Terminal-Bench | ~82.7% (TB2.1) |
| Input price / 1M | $5 |
| Output price / 1M | $25 |
| Context window | 1M |
| Open weights | No |
| Access | API · Claude Code · claude.ai (Max) |
| Maker | Anthropic |
how good is Claude Opus 4.8 at coding?
Claude Opus 4.8 sits at #3 of 13 ranked models, posting 88.6% on SWE-bench Verified — 7.6 points behind #1 GPT-5.6 Sol. On the harder SWE-bench Pro it scores 69.2%. Terminal-Bench (agentic terminal work): ~82.7% (TB2.1).
Score provenance: Independent (vals.ai, Jul 14 2026, mini-swe-agent bash-only harness): SWE-bench Verified 88.6% ±1.42. Corrected Jul 17, 2026: we previously printed Anthropic's own "~86%" and claimed independent evals tracked it within ~1 point, which was wrong — the independent number is 2.6 points higher, and our methodology is to prefer the independent one. Run through the Claude Code harness instead of the bare bash agent, vals.ai measures 85.8%, a reminder that the harness moves these numbers as much as the model does. SWE-bench Pro 69.2% is Anthropic-reported.
what does Claude Opus 4.8 cost?
$5 per 1M input tokens and $25 per 1M output — #11 cheapest of the 13 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
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-17.