Claude Sonnet 4.5 vs GPT-5

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

OpenAI · Aug 2025

70.7

OpenAI's August 2025 unified flagship that merged the GPT and o-series reasoning lines into one model with selectable effort.

The verdict

GPT-5 wins 4 of the 6 benchmarks these models share, against 2 for Claude Sonnet 4.5. GPT-5 is about 1.7x cheaper per blended million tokens (3:1 input:output mix). GPT-5 also takes 400K of context versus 200K for Claude Sonnet 4.5.

Benchmark head-to-head 24

SWE-bench Verified
77.2%74.9%
Claude Sonnet 4.5GPT-5
GPQA Diamond
83.4%85.7%
Claude Sonnet 4.5GPT-5
AIME 2025
87%94.6%
Claude Sonnet 4.5GPT-5
HLE
~17.3%24.8%
Claude Sonnet 4.5GPT-5
Terminal-Bench
50%~43.8%
Claude Sonnet 4.5GPT-5
MMMU
~77.8%84.2%
Claude Sonnet 4.5GPT-5

Specs & pricing

Claude Sonnet 4.5GPT-5
modhub Index65.570.7
Input price / 1M$3$1.25
Output price / 1M$15$10
Context window200K400K
Max output64K128K
Open weightsnono
Reasoning modelyesyes
Multimodal inputtext, imagetext, image
Knowledge cutoffJan 2025Sep 2024
ReleasedSep 2025Aug 2025
Example monthly cost*$52.50$27.50

* 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?
GPT-5 wins 4 of the 6 benchmarks these models share, against 2 for Claude Sonnet 4.5. GPT-5 is about 1.7x cheaper per blended million tokens (3:1 input:output mix). GPT-5 also takes 400K of context versus 200K for Claude Sonnet 4.5.
Which is cheaper, Claude Sonnet 4.5 or GPT-5?
Claude Sonnet 4.5 costs $3/$15 per million input/output tokens, while GPT-5 costs $1.25/$10. For a typical workload of 10M input and 1.5M output tokens per month, that's $52.50 versus $27.50.
Which model is better for coding, Claude Sonnet 4.5 or GPT-5?
On SWE-bench Verified — the standard agentic-coding benchmark — Claude Sonnet 4.5 scores 77.2% versus 74.9% for GPT-5, making Claude Sonnet 4.5 the stronger pick for coding agents.

More comparisons