Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
1.05M256k
API pricing
Input price
$4.00—
Output price
$20.00—
Cached input price
$0.40—
Cheapest input
$2.00OpenAI—
Cheapest output
$10.00OpenAI—
$1,800OpenAI list price—
Benchmarks
BrowseComp
90.4%63.8%
GPQA Diamond
94.6%86.6%
MMMU-Pro
83%76.9%
Overview
CompanyOpenAIQwen
Release dateJun 26 2026Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.6 Sol leads Qwen3.5 Medium on 3 of the 3 benchmarks they both report (BrowseComp, GPQA Diamond, MMMU-Pro). Only GPT-5.6 Sol has a verified first-party price for an available API: $4.00 per million input tokens and $20.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. Qwen3.5 Medium shipped 122 days before GPT-5.6 Sol, so benchmark comparisons should account for the intervening progress.

Context windows are 1.05M (GPT-5.6 Sol) vs 256k (Qwen3.5 Medium). GPT-5.6 Sol is closed, while Qwen3.5 Medium is open weight.

On BrowseComp, GPT-5.6 Sol leads at 90.4% vs Qwen3.5 Medium at 63.8%. On GPQA Diamond, GPT-5.6 Sol leads at 94.6% vs Qwen3.5 Medium at 86.6%. On MMMU-Pro, GPT-5.6 Sol leads at 83% vs Qwen3.5 Medium at 76.9%.