Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
Benchmarks
Humanity's Last Exam · no tools
40.2%24%
CharXiv Reasoning
84.2%78.4%
MMMU-Pro
83.6%75.8%
Overview
CompanyGoogleQwen
Release dateMay 19 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash leads Qwen3.6-27B on 3 of the 3 benchmarks they both report (Humanity's Last Exam, CharXiv Reasoning, MMMU-Pro). Qwen3.6-27B shipped 27 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.5 Flash) vs 256k (Qwen3.6-27B). Gemini 3.5 Flash is closed, while Qwen3.6-27B is open weight.

On Humanity's Last Exam · no tools, Gemini 3.5 Flash leads at 40.2% vs Qwen3.6-27B at 24%. On CharXiv Reasoning, Gemini 3.5 Flash leads at 84.2% vs Qwen3.6-27B at 78.4%. On MMMU-Pro, Gemini 3.5 Flash leads at 83.6% vs Qwen3.6-27B at 75.8%.