# Claude Opus 4.8 vs DeepSeek V3.2 Exp Thinking

As of Oct 15, 2026, Claude Opus 4.8 leads DeepSeek V3.2 Exp Thinking in 4 of 4 shared categories: General LLM, Reasoning, Long context, and Factuality.

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

DeepSeek V3.2 Exp Thinking: price per 1M tokens is unset in the catalog.

Claude Opus 4.8: closed weights.

DeepSeek V3.2 Exp Thinking: open weights.

- Which to pick, General LLM: As of Oct 15, 2026, Claude Opus 4.8 leads DeepSeek V3.2 Exp Thinking in General LLM at #21 against #111.
- Which to pick, Reasoning: As of Oct 15, 2026, Claude Opus 4.8 leads DeepSeek V3.2 Exp Thinking in Reasoning at #10 against #109.
- Which to pick, Long context: As of Oct 15, 2026, Claude Opus 4.8 leads DeepSeek V3.2 Exp Thinking in Long context at #10 against #111.
- Which to pick, Factuality: As of Oct 15, 2026, Claude Opus 4.8 leads DeepSeek V3.2 Exp Thinking in Factuality at #24 against #68.

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, DeepSeek V3.2 Exp Thinking is ranked #68 in Factuality (since Oct 15, 2026; sources LMArena Text factuality; methodology v1.0).