# Claude Opus 4.7 vs DeepSeek R1 0528

As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in 5 of 5 shared categories: General LLM, Reasoning, Science, Long context, and Abstraction (ARC).

Claude Opus 4.7: $10 per 1M blended tokens.

DeepSeek R1 0528: $0.9125000000000001 per 1M blended tokens.

Claude Opus 4.7: closed weights.

DeepSeek R1 0528: open weights.

- Which to pick, General LLM: As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in General LLM at #5 against #92.
- Which to pick, Reasoning: As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in Reasoning at #4 against #98.
- Which to pick, Science: As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in Science at #34 against #78.
- Which to pick, Long context: As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in Long context at #4 against #114.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, Claude Opus 4.7 leads DeepSeek R1 0528 in Abstraction (ARC) at #11 against #70.

As of Oct 14, 2026, Claude Opus 4.7 is near state of the art, rank #4 in Reasoning (since Oct 14, 2026; sources LMArena Text (style-controlled, hard prompts); methodology v1.0).

As of Oct 14, 2026, DeepSeek R1 0528 is a former state-of-the-art holder in General LLM (since Aug 7, 2025; sources LMArena Text (style-controlled, overall); methodology v1.0).