Compare AI models

Specifications
Parameters
—27B/35B/122B
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%72%
Humanity's Last Exam · no tools
8.7%25.3%
GPQA Diamond
71.2%86.6%
MMMU
75.6%83.9%
Overview
CompanyOpenAIQwen
Release dateAug 7 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium 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 Qwen3.5 Medium. GPT-5 nano shipped 201 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs GPT-5 nano at 54.7%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs GPT-5 nano at 8.7%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs GPT-5 nano at 71.2%. On MMMU, Qwen3.5 Medium leads at 83.9% vs GPT-5 nano at 75.6%.