Anthropicpreview
Claude 4.8 Opus
Released at: May 18, 2026
API StatusAvailable for integration
Context Window1,000,000 tokens
Input Price / MTok$5.00
Output Price / MTok$25.00
Model Overview
Anthropic's most advanced reasoning model. Unmatched capabilities in deep coding repair, multi-modal document research, and autonomous software engineering.
Vetted Benchmarks
mmluScore: 95.4% (Ranked top 4%)
humanevalScore: 97.2% (Ranked top 4%)
mathScore: 94.1% (Ranked top 9%)
gpqaScore: 86.5% (Ranked top 4%)
mt_benchScore: 9.8% (Ranked top 4%)
hellaswagScore: 99.2% (Ranked top 4%)
Input Price TrendLast 90 Days
Output Price TrendLast 90 Days
How does this model compare?
Evaluate benchmark standing and performance rankings vs all other tracked models.