# Claude Opus 4.8 vs Claude Opus 5

As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 5 in 0 of 10 shared categories.

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

Claude Opus 5: $10 per 1M blended tokens.

Claude Opus 4.8: closed weights.

Claude Opus 5: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in General LLM at #11 against #21.
- Which to pick, Reasoning: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Reasoning at #9 against #10.
- Which to pick, Science: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Science at #12 against #27.
- Which to pick, Coding: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Coding at #4 against #12.
- Which to pick, Coding › Agentic: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Coding › Agentic at #4 against #12.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Coding › Web dev at #6 against #35.
- Which to pick, Long context: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Long context at #9 against #10.
- Which to pick, Vision: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Vision at #12 against #13.
- Which to pick, Factuality: As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Factuality at #4 against #24.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, Claude Opus 5 leads Claude Opus 4.8 in Abstraction (ARC) at #3 against #12.

As of Oct 15, 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 15, 2026, Claude Opus 5 is near state of the art, rank #4 in Factuality (since Oct 15, 2026; sources LMArena Text factuality; methodology v1.0).