When was Claude Sonnet 4.5 released?

Claude Sonnet 4.5 was released by Anthropic on Sep 29 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 4.5 or GPT-5.2?

GPT-5.2 scores higher on GPQA Diamond — Claude Sonnet 4.5 83.4% vs GPT-5.2 92.4%.

Which is better at coding, Claude Sonnet 4.5 or GPT-5.2?

On SWE-Bench Verified (real-world software-engineering tasks), GPT-5.2 leads — Claude Sonnet 4.5 scores 77.2% and GPT-5.2 scores 80%.

Home Analytics Contact

Latest Release

Muse Spark

Apr 8 2026

Home/Compare/Claude Sonnet 4.5 vs GPT-5.2

Claude Sonnet 4.5 vs GPT-5.2

1 vs 2 benchmarks won

	Anthropic Claude Sonnet 4.5	OpenAI GPT-5.2
Overview
Company	Anthropic	OpenAI
Release date	Sep 29 2025	Dec 11 2025
Model type	—	—
Open source	No	No
Specifications
Parameters	—	—
Context window	—	—
Benchmarks
Science reasoning GPQA Diamond	83.4%	92.4%
Software engineering SWE-Bench Verified	77.2%	80%
Multimodal understanding MMMU	68%	—
Timeline
Release gap	Claude Sonnet 4.5 shipped 73 days before GPT-5.2

Which is better: Claude Sonnet 4.5 or GPT-5.2?

GPT-5.2 leads Claude Sonnet 4.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4.5 shipped 73 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%, 9 points above Claude Sonnet 4.5 at 83.4%. On SWE-Bench Verified, GPT-5.2 scores 80%, 2.8 points above Claude Sonnet 4.5 at 77.2%.

Frequently asked questions

When was Claude Sonnet 4.5 released?: Claude Sonnet 4.5 was released by Anthropic on Sep 29 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 4.5 or GPT-5.2?: GPT-5.2 scores higher on GPQA Diamond — Claude Sonnet 4.5 83.4% vs GPT-5.2 92.4%.
Which is better at coding, Claude Sonnet 4.5 or GPT-5.2?: On SWE-Bench Verified (real-world software-engineering tasks), GPT-5.2 leads — Claude Sonnet 4.5 scores 77.2% and GPT-5.2 scores 80%.