Claude Sonnet 4.5

Released

Claude Sonnet 4.5 is an AI model released by Anthropic on Monday, Sep 29 2025, 55 days after Claude Opus 4.1. Benchmark results (shown below) cover BullshitBench v2, SWE-Bench Verified, Next.js Evals, ARC-AGI-2, GPQA Diamond, OSWorld-Verified, and 1 more.

API pricing

Input
$3.00
Cached input
$0.30
5 min cache write
$3.75
1 hr cache write
$6.00
Output
$15.00
  • Reasoning or thinking is supported.
USD per 1M tokens

Available from

Amazon Bedrock$3.00$15.001M
Azureglobal$3.00$15.00200K
Googleglobal$3.00$15.001M
Amazon Bedrockeu-west-1$3.30$16.501M
Googleus-east5$3.30$16.501M
USD per 1M tokens

Benchmarks

Coding

SWE-Bench Verified
77.2%
#23 of 57
Next.js Evals
39%
#27 of 28

Agentic & tool use

OSWorld-Verified
61.4%
#25 of 28

Reasoning & science

ARC-AGI-2
13.6%
#21 of 21
GPQA Diamond
83.4%
#33 of 59

Multimodal

MMMU
68%
#6 of 7

Robustness

BullshitBench v2
79%
#8 of 77

Source: BenchLM, retrieved 31 August 2026. Every other score here is the figure the lab published at launch.

About

Claude Sonnet 4.5, released September 29, 2025, was introduced by Anthropic as the best coding model in the world at the time. It reached 77.2% on SWE-Bench Verified and 83.4% on GPQA Diamond, and it was built for autonomy: Anthropic reported it could work productively on complex, multi-step tasks for many hours without losing the thread — the capability that underpinned the Claude Agent SDK, released the same day.

Beyond raw scores, Sonnet 4.5 marked the point where the mid-tier Sonnet line overtook the previous flagship Opus 4.1 on software-engineering benchmarks while remaining far cheaper, a pattern that repeated across the industry as labs pushed agentic training into smaller models. It was succeeded at the top of the coding leaderboards by Claude Opus 4.5 in November 2025.

Compare Claude Sonnet 4.5 with

Claude Sonnet 4.5

Suggested comparisons

Frequently asked questions

Claude Sonnet 4.5 was released by Anthropic on Monday, Sep 29 2025.

All Anthropic releases

27 tracked