Compare AI models

Specifications
Parameters
—27B
Context window
400k256k
API pricing
Input price
$0.05—
Output price
$0.40—
Cached input price
$0.005—
Cheapest input
$0.025OpenAI—
Cheapest output
$0.20OpenAI—
$30.00OpenAI list price—
Benchmarks
SWE-Bench Verified
54.7%77.2%
Humanity's Last Exam · no tools
8.7%24%
GPQA Diamond
71.2%87.8%
MMMU
75.6%82.9%
Overview
CompanyOpenAIQwen
Release dateAug 7 2025Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads GPT-5 nano on 4 of the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond, MMMU). Only GPT-5 nano has a verified first-party price for an available API: $0.05 per million input tokens and $0.40 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. GPT-5 nano shipped 258 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5 nano) vs 256k (Qwen3.6-27B). GPT-5 nano is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs GPT-5 nano at 54.7%. On Humanity's Last Exam · no tools, Qwen3.6-27B leads at 24% vs GPT-5 nano at 8.7%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs GPT-5 nano at 71.2%. On MMMU, Qwen3.6-27B leads at 82.9% vs GPT-5 nano at 75.6%.