Compare AI models

Specifications
Parameters
—27B
Context window
400k256k
API pricing
Input price
$0.75—
Output price
$4.50—
Cached input price
$0.075—
Cheapest input
$0.375OpenAI—
Cheapest output
$2.25OpenAI—
$375OpenAI list price—
Benchmarks
Terminal-Bench 2.0
60%59.3%
Humanity's Last Exam · no tools
28.2%24%
GPQA Diamond
88%87.8%
MMMU-Pro
76.6%75.8%
Overview
CompanyOpenAIQwen
Release dateMar 17 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.4 mini leads Qwen3.6-27B on 4 of the 4 benchmarks they both report (Terminal-Bench 2.0, Humanity's Last Exam, GPQA Diamond, MMMU-Pro). Only GPT-5.4 mini has a verified first-party price for an available API: $0.75 per million input tokens and $4.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. GPT-5.4 mini shipped 36 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.4 mini) vs 256k (Qwen3.6-27B). GPT-5.4 mini is closed, while Qwen3.6-27B is open weight.

On Terminal-Bench 2.0, GPT-5.4 mini leads at 60% vs Qwen3.6-27B at 59.3%. On Humanity's Last Exam · no tools, GPT-5.4 mini leads at 28.2% vs Qwen3.6-27B at 24%. On GPQA Diamond, GPT-5.4 mini leads at 88% vs Qwen3.6-27B at 87.8%. On MMMU-Pro, GPT-5.4 mini leads at 76.6% vs Qwen3.6-27B at 75.8%.