Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Input price
$0.50—
Output price
$3.00—
Cached input price
$0.05—
Cheapest input
$0.25Google AI Studio—
Cheapest output
$1.50Google AI Studio—
$250Google list price—
Benchmarks
SWE-Bench Verified
78%77.2%
Terminal-Bench 2.0
47.6%59.3%
Humanity's Last Exam · no tools
33.7%24%
GPQA Diamond
90.4%87.8%
CharXiv Reasoning
80.3%78.4%
MMMU-Pro
81.2%75.8%
Overview
CompanyGoogleQwen
Release dateDec 17 2025Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Flash leads Qwen3.6-27B on 5 of the 6 benchmarks they both report. Only Gemini 3.0 Flash has a verified first-party price for an available API: $0.50 per million input tokens and $3.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Gemini 3.0 Flash shipped 126 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.0 Flash) vs 256k (Qwen3.6-27B). Gemini 3.0 Flash is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Gemini 3.0 Flash leads at 78% vs Qwen3.6-27B at 77.2%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs Gemini 3.0 Flash at 47.6%. On Humanity's Last Exam · no tools, Gemini 3.0 Flash leads at 33.7% vs Qwen3.6-27B at 24%. On GPQA Diamond, Gemini 3.0 Flash leads at 90.4% vs Qwen3.6-27B at 87.8%. On CharXiv Reasoning, Gemini 3.0 Flash leads at 80.3% vs Qwen3.6-27B at 78.4%. On MMMU-Pro, Gemini 3.0 Flash leads at 81.2% vs Qwen3.6-27B at 75.8%.