Claude Opus 4.8

0M · Q4_K_M · ~0.0 GB

How good is it? — per-capability quality

Each number is the model’s score on its best public benchmarkfor that skill — named and linked below, never a blend. Scores compare cleanly when the benchmark matches; benchmarks are gameable, so we show the receipts rather than hide behind one number.

Coding89

SWE-Bench Verified · source · as of 2026-06

Math & logic—

Not yet scored on a benchmark we can cite — left blank rather than guessed.

General94

GPQA · source · as of 2026-06

Anthropic's flagship — frontier reasoning, coding and agentic work. Cloud-only (subscription / API).

About this model

Context window: 200,000 tokens

Will Claude Opus 4.8 actually run on YOUR graphics card?

This page shows fit for a generic VRAM tier. Tell us your GPU for a personalized speed estimate and fit verdict.

Enter your graphics card →