# Claude Opus 4.8 vs Claude Sonnet 5

As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in 8 of 8 shared categories: General LLM, Reasoning, Science, Coding, Coding › Agentic, Coding › Web dev, Long context, and Factuality.

Claude Opus 4.8: $10 per 1M blended tokens.

Claude Sonnet 5: $4.000000000000001 per 1M blended tokens.

Claude Opus 4.8: closed weights.

Claude Sonnet 5: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in General LLM at #20 against #39.
- Which to pick, Reasoning: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Reasoning at #10 against #34.
- Which to pick, Science: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Science at #27 against #32.
- Which to pick, Coding: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Coding at #12 against #19.
- Which to pick, Coding › Agentic: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Coding › Agentic at #12 against #19.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Coding › Web dev at #33 against #38.
- Which to pick, Long context: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Long context at #10 against #31.
- Which to pick, Factuality: As of Oct 14, 2026, Claude Opus 4.8 leads Claude Sonnet 5 in Factuality at #21 against #47.

As of Oct 14, 2026, Claude Opus 4.8 is a former state-of-the-art holder in Coding › Web dev (since Jun 5, 2026; sources LMArena WebDev; methodology v1.0).

As of Oct 14, 2026, Claude Sonnet 5 is ranked #19 in Coding (since Oct 14, 2026; sources Terminal-Bench 4.0; methodology v1.0).