Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
1M256k
Benchmarks
SWE-Bench Verified
76.2%72%
Terminal-Bench 2.0
54.2%49.4%
BrowseComp
59.2%63.8%
Humanity's Last Exam · no tools
37.5%25.3%
Humanity's Last Exam · with tools
45.8%47.5%
GPQA Diamond
91.9%86.6%
CharXiv Reasoning
81.4%77.2%
MMMU-Pro
81%76.9%
Overview
CompanyGoogleQwen
Release dateNov 18 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Pro leads Qwen3.5 Medium on 6 of the 8 benchmarks they both report. Gemini 3.0 Pro shipped 98 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.0 Pro) vs 256k (Qwen3.5 Medium). Gemini 3.0 Pro is closed, while Qwen3.5 Medium is open weight.

On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs Qwen3.5 Medium at 72%. On Terminal-Bench 2.0, Gemini 3.0 Pro leads at 54.2% vs Qwen3.5 Medium at 49.4%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Gemini 3.0 Pro at 59.2%. On Humanity's Last Exam · no tools, Gemini 3.0 Pro leads at 37.5% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Qwen3.5 Medium leads at 47.5% vs Gemini 3.0 Pro at 45.8%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Qwen3.5 Medium at 86.6%. On CharXiv Reasoning, Gemini 3.0 Pro leads at 81.4% vs Qwen3.5 Medium at 77.2%. On MMMU-Pro, Gemini 3.0 Pro leads at 81% vs Qwen3.5 Medium at 76.9%.