Claude Sonnet 4.5 vs GPT-5 mini

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 mini

OpenAI · Aug 2025

A fast, cheap distillation of GPT-5 for high-volume workloads — one fifth of the flagship's price with most of its everyday capability.

The verdict

Claude Sonnet 4.5 wins 2 of the 3 benchmarks these models share, against 1 for GPT-5 mini. On price the gap is dramatic: GPT-5 mini works out roughly 8.7x cheaper per blended million tokens. GPT-5 mini also takes 400K of context versus 200K for Claude Sonnet 4.5.

Benchmark head-to-head 21

SWE-bench Verified
77.2%~71%
Claude Sonnet 4.5GPT-5 mini
GPQA Diamond
83.4%~82.3%
Claude Sonnet 4.5GPT-5 mini
AIME 2025
87%~91.1%
Claude Sonnet 4.5GPT-5 mini

Specs & pricing

Claude Sonnet 4.5GPT-5 mini
modhub Index65.5
Input price / 1M$3$0.25
Output price / 1M$15$2
Context window200K400K
Max output64K128K
Open weightsnono
Reasoning modelyesyes
Multimodal inputtext, imagetext, image
Knowledge cutoffJan 2025May 2024
ReleasedSep 2025Aug 2025
Example monthly cost*$52.50$5.50

* 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 mini?
Claude Sonnet 4.5 wins 2 of the 3 benchmarks these models share, against 1 for GPT-5 mini. On price the gap is dramatic: GPT-5 mini works out roughly 8.7x cheaper per blended million tokens. GPT-5 mini also takes 400K of context versus 200K for Claude Sonnet 4.5.
Which is cheaper, Claude Sonnet 4.5 or GPT-5 mini?
Claude Sonnet 4.5 costs $3/$15 per million input/output tokens, while GPT-5 mini costs $0.25/$2. For a typical workload of 10M input and 1.5M output tokens per month, that's $52.50 versus $5.50.
Which model is better for coding, Claude Sonnet 4.5 or GPT-5 mini?
On SWE-bench Verified — the standard agentic-coding benchmark — Claude Sonnet 4.5 scores 77.2% versus ~71% for GPT-5 mini, making Claude Sonnet 4.5 the stronger pick for coding agents.

More comparisons