When was Claude Sonnet 4 released?

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

When was GPT-5.2 released?

GPT-5.2 was released by OpenAI on Dec 11 2025.

Which is better on GPQA Diamond, Claude Sonnet 4 or GPT-5.2?

GPT-5.2 scores higher on GPQA Diamond — Claude Sonnet 4 75.4% vs GPT-5.2 92.4%.

Which is better at coding, Claude Sonnet 4 or GPT-5.2?

On SWE-Bench Verified (real-world software-engineering tasks), GPT-5.2 leads — Claude Sonnet 4 scores 72.7% and GPT-5.2 scores 80%.

Home Analytics Contact

Latest Release

Muse Spark

Apr 8 2026

Home/Compare/Claude Sonnet 4 vs GPT-5.2

Claude Sonnet 4 vs GPT-5.2

0 vs 2 benchmarks won

	Anthropic Claude Sonnet 4	OpenAI GPT-5.2
Overview
Company	Anthropic	OpenAI
Release date	May 22 2025	Dec 11 2025
Model type	—	—
Open source	No	No
Specifications
Parameters	—	—
Context window	—	—
Benchmarks
Science reasoning GPQA Diamond	75.4%	92.4%
Software engineering SWE-Bench Verified	72.7%	80%
Multimodal understanding MMMU	—	—
Timeline
Release gap	Claude Sonnet 4 shipped 203 days before GPT-5.2

Which is better: Claude Sonnet 4 or GPT-5.2?

GPT-5.2 leads Claude Sonnet 4 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4 shipped 203 days before GPT-5.2, 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 GPQA Diamond, GPT-5.2 scores 92.4%, 17 points above Claude Sonnet 4 at 75.4%. On SWE-Bench Verified, GPT-5.2 scores 80%, 7.3 points above Claude Sonnet 4 at 72.7%.

Frequently asked questions

When was Claude Sonnet 4 released?: Claude Sonnet 4 was released by Anthropic on May 22 2025.
When was GPT-5.2 released?: GPT-5.2 was released by OpenAI on Dec 11 2025.
Which is better on GPQA Diamond, Claude Sonnet 4 or GPT-5.2?: GPT-5.2 scores higher on GPQA Diamond — Claude Sonnet 4 75.4% vs GPT-5.2 92.4%.
Which is better at coding, Claude Sonnet 4 or GPT-5.2?: On SWE-Bench Verified (real-world software-engineering tasks), GPT-5.2 leads — Claude Sonnet 4 scores 72.7% and GPT-5.2 scores 80%.