Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
1.05M256k
API pricing
Input price
$30.00—
Output price
$180.00—
Cheapest input
$30.00OpenAI—
Cheapest output
$180.00OpenAI—
$15,000OpenAI list price—
Benchmarks
BrowseComp
90.1%63.8%
Humanity's Last Exam · no tools
43.1%25.3%
Humanity's Last Exam · with tools
57.2%47.5%
Overview
CompanyOpenAIQwen
Release dateApr 23 2026Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.5-Pro leads Qwen3.5 Medium on 3 of the 3 benchmarks they both report (BrowseComp, Humanity's Last Exam). Only GPT-5.5-Pro has a verified first-party price for an available API: $30.00 per million input tokens and $180.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. Qwen3.5 Medium shipped 58 days before GPT-5.5-Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 1.05M (GPT-5.5-Pro) vs 256k (Qwen3.5 Medium). GPT-5.5-Pro is closed, while Qwen3.5 Medium is open weight.

On BrowseComp, GPT-5.5-Pro leads at 90.1% vs Qwen3.5 Medium at 63.8%. On Humanity's Last Exam · no tools, GPT-5.5-Pro leads at 43.1% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, GPT-5.5-Pro leads at 57.2% vs Qwen3.5 Medium at 47.5%.