Claude Opus 4vsClaude Opus 4.1

Claude Opus 4
Claude Opus 4.1
Benchmarks
Nonsense detection
BullshitBench v2
34%
43%Best
Coding
SWE-Bench Verified
72.5%
74.5%Best
Science
GPQA Diamond
79.6%
80.9%Best
Overview
CompanyAnthropicAnthropic
Release dateMay 22 2025Aug 5 2025
AccessProprietaryProprietary

Which is better: Claude Opus 4 or Claude Opus 4.1?

Claude Opus 4.1 leads Claude Opus 4 on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude Opus 4 shipped 75 days before Claude Opus 4.1, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, Claude Opus 4.1 leads at 43% vs Claude Opus 4 at 34%. On SWE-Bench Verified, Claude Opus 4.1 leads at 74.5% vs Claude Opus 4 at 72.5%. On GPQA Diamond, Claude Opus 4.1 leads at 80.9% vs Claude Opus 4 at 79.6%.

Frequently asked questions

Claude Opus 4 was released by Anthropic on May 22 2025.

Claude Opus 4.1 was released by Anthropic on Aug 5 2025.

Claude Opus 4.1 leads on SWE-Bench Verified — Claude Opus 4 72.5% vs Claude Opus 4.1 74.5%.

Claude Opus 4.1 leads on GPQA Diamond — Claude Opus 4 79.6% vs Claude Opus 4.1 80.9%.

Other comparisons