Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
400k256k
API pricing
Input price
$1.25—
Output price
$10.00—
Cached input price
$0.125—
Cheapest input
$1.25Azure—
Cheapest output
$10.00Azure—
$750OpenAI list price—
Benchmarks
SWE-Bench Verified
74.9%72%
Humanity's Last Exam · no tools
24.8%25.3%
GPQA Diamond
85.7%86.6%
MMMU
84.2%83.9%
Overview
CompanyOpenAIQwen
Release dateAug 7 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5 and Qwen3.5 Medium are evenly matched across the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond, MMMU). Only GPT-5 has a verified first-party price for an available API: $1.25 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. GPT-5 shipped 201 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, GPT-5 leads at 74.9% vs Qwen3.5 Medium at 72%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs GPT-5 at 24.8%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs GPT-5 at 85.7%. On MMMU, GPT-5 leads at 84.2% vs Qwen3.5 Medium at 83.9%.