Claude Sonnet 4.5 vs GPT-5.2

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Claude Sonnet 4.5

Anthropic · Sep 2025

65.5

The model that made 30-hour autonomous coding sessions real — 77.2% SWE-bench Verified and a 1M-token context beta at $3/$15.

GPT-5.2

OpenAI · Dec 2025

The December 2025 GPT-5 refresh: stronger coding and agentic skills than GPT-5.1 at a moderate price, now the value pick in OpenAI's lineup.

The verdict

GPT-5.2 wins 1 of the 1 benchmarks these models share, against 0 for Claude Sonnet 4.5. GPT-5.2 is about 1.2x cheaper per blended million tokens (3:1 input:output mix). GPT-5.2 also takes 400K of context versus 200K for Claude Sonnet 4.5.

Benchmark head-to-head 01

SWE-bench Verified
77.2%~77.9%
Claude Sonnet 4.5GPT-5.2

Specs & pricing

Claude Sonnet 4.5GPT-5.2
modhub Index65.5
Input price / 1M$3$1.75
Output price / 1M$15$14
Context window200K400K
Max output64K128K
Open weightsnono
Reasoning modelyesyes
Multimodal inputtext, imagetext, image
Knowledge cutoffJan 2025Aug 2025
ReleasedSep 2025Dec 2025
Example monthly cost*$52.50$38.50

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Claude Sonnet 4.5 or GPT-5.2?
GPT-5.2 wins 1 of the 1 benchmarks these models share, against 0 for Claude Sonnet 4.5. GPT-5.2 is about 1.2x cheaper per blended million tokens (3:1 input:output mix). GPT-5.2 also takes 400K of context versus 200K for Claude Sonnet 4.5.
Which is cheaper, Claude Sonnet 4.5 or GPT-5.2?
Claude Sonnet 4.5 costs $3/$15 per million input/output tokens, while GPT-5.2 costs $1.75/$14. For a typical workload of 10M input and 1.5M output tokens per month, that's $52.50 versus $38.50.
Which model is better for coding, Claude Sonnet 4.5 or GPT-5.2?
On SWE-bench Verified — the standard agentic-coding benchmark — GPT-5.2 scores ~77.9% versus 77.2% for Claude Sonnet 4.5, making GPT-5.2 the stronger pick for coding agents.

More comparisons