Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Input price
$2.00—
Output price
$12.00—
Cached input price
$0.20—
Cheapest input
$1.00Google AI Studio—
Cheapest output
$6.00Google AI Studio—
$1,000Google list price—
Benchmarks
SWE-Bench Verified
80.6%77.2%
Terminal-Bench 2.0
68.5%59.3%
Humanity's Last Exam · no tools
44.4%24%
GPQA Diamond
94.3%87.8%
CharXiv Reasoning
83.3%78.4%
MMMU-Pro
80.5%75.8%
Overview
CompanyGoogleQwen
Release dateFeb 19 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.1 Pro leads Qwen3.6-27B on 6 of the 6 benchmarks they both report. Only Gemini 3.1 Pro has a verified first-party price for an available API: $2.00 per million input tokens and $12.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Gemini 3.1 Pro shipped 62 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.1 Pro) vs 256k (Qwen3.6-27B). Gemini 3.1 Pro is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Gemini 3.1 Pro leads at 80.6% vs Qwen3.6-27B at 77.2%. On Terminal-Bench 2.0, Gemini 3.1 Pro leads at 68.5% vs Qwen3.6-27B at 59.3%. On Humanity's Last Exam · no tools, Gemini 3.1 Pro leads at 44.4% vs Qwen3.6-27B at 24%. On GPQA Diamond, Gemini 3.1 Pro leads at 94.3% vs Qwen3.6-27B at 87.8%. On CharXiv Reasoning, Gemini 3.1 Pro leads at 83.3% vs Qwen3.6-27B at 78.4%. On MMMU-Pro, Gemini 3.1 Pro leads at 80.5% vs Qwen3.6-27B at 75.8%.