Anthropic says Claude changes its personality across languages and models

Q: Which Claude models did Anthropic compare when mapping personality differences?

Anthropic compared multiple Claude models, including Fable 5 and Sonnet, and specifically noted differences between Opus 4.7 (more critical and challenging) and Sonnet 4.6 (faster and more affirming).

Q: How did Anthropic measure Claude’s behavior across different languages and models?

Anthropic analyzed over 300,000 real user interactions and mapped Claude’s behavior across four key personality traits to measure how its tone and approaches varied by model and language.

Q: Which specific personality traits did the report map across Claude’s models?

The report mapped Claude’s behavior across four key personality traits. It found variations such as Opus 4.7 being more critical and challenging, Sonnet 4.6 being faster and more affirming, and language effects like warmer responses in Hindi and Arabic versus more analytical and skeptical tones in English and Russian.

Q: How do Opus 4.7 and Sonnet 4.6 differ in tone and response style according to the report?

According to Anthropic's report, Opus 4.7 is more critical and challenging in tone, while Sonnet 4.6 is faster and more affirming in its responses. The report frames these differences as personality shifts across models rather than judgments of which model is better.

Anthropic's new research shows Claude's tone shifts by AI model and language, from warm and affirming to more rigorous and skeptical.

VIEW GALLERY - 5

Jak Connor

Tech and Science Editor

Published Jul 14, 2026 9:34 AM CDT

1 minute & 30 seconds read time

TL;DR: Anthropic found Claude's behavior varies by model and language: different models (e.g., Opus 4.7 vs Sonnet 4.6) show distinct tones and approaches, and responses are warmer in Hindi and Arabic but more analytical in English and Russian, affecting suitability rather than indicating a universally better model.

Voice: Jak ConnorSpeed

0:00 / 2:00

Claude isn't just adapting to your questions; it's adapting to you, as Anthropic has officially confirmed that the AI chatbot's behavior shifts depending on both the model you pick and the language you use, resulting in a variation of tone and approaches to problem-solving questions.

Anthropic says Claude changes its personality across languages and models 1

VIEW GALLERY - 5 IMAGES

In a nutshell, Claude changes its "personality" depending on the model that is being used, meaning the Claude you interact with when using Fable 5 is different than the Claude you interacted with when using the Sonnet model. Anthropic has published a report where it reveals it analyzed over 300,000 real user interactions and mapped Claude's behavior across four key personality traits.

The results show that Opus 4.7 is more critical and challenging, while Sonnet 4.6 is faster and more affirming. Meanwhile, language choice also plays its own role in the generated response, as it was discovered that Claude comes across as warmer in Hindi and Arabic, but more analytical and skeptical in English and Russian.

Anthropic says Claude changes its personality across languages and models 3

This dynamic behavior raises important questions for anyone relying on AI for real-world decisions or looking to get the most out of their token usage, as these results aren't indicative of what model is "better," as the "best" model completely depends on the job you need to complete.

Anthropic says Claude changes its personality across languages and models 4

Frequently Asked Questions

TweakBot answers common questions about this news using TweakTown's own coverage from this page and related content from our archive. Tap a question to reveal the answer, or type your own below.

Question #1

Which Claude models did Anthropic compare when mapping personality differences?

Question #2

How did Anthropic measure Claude’s behavior across different languages and models?

Question #3

Which specific personality traits did the report map across Claude’s models?

Question #4

How do Opus 4.7 and Sonnet 4.6 differ in tone and response style according to the report?

Have a question not listed here? Ask below and TweakBot will answer it.

Interestingly, Anthropic notes it's unclear whether these shifts are a flaw or a feature, but for now, it's a tool users can leverage to get a more balanced perspective, or at the very least, understand there are fundamental differences between each of the models in aspects that aren't just performance or efficiency.