Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
1M256k
API pricing
Input price
$0.25—
Output price
$1.50—
Cached input price
$0.025—
Cheapest input
$0.125Google AI Studio—
Cheapest output
$0.75Google AI Studio—
$125Google list price—
Benchmarks
LiveCodeBench
72%78.9%
Humanity's Last Exam · no tools
16%25.3%
GPQA Diamond
86.9%86.6%
OSWorld-Verified
54.3%58%
CharXiv Reasoning
73.2%77.2%
MMMU-Pro
76.8%76.9%
Overview
CompanyGoogleQwen
Release dateMar 3 2026Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Gemini 3.1 Flash-Lite on 5 of the 6 benchmarks they both report. Only Gemini 3.1 Flash-Lite has a verified first-party price for an available API: $0.25 per million input tokens and $1.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. Qwen3.5 Medium shipped 7 days before Gemini 3.1 Flash-Lite, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.1 Flash-Lite) vs 256k (Qwen3.5 Medium). Gemini 3.1 Flash-Lite is closed, while Qwen3.5 Medium is open weight.

On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs Gemini 3.1 Flash-Lite at 72%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs Gemini 3.1 Flash-Lite at 16%. On GPQA Diamond, Gemini 3.1 Flash-Lite leads at 86.9% vs Qwen3.5 Medium at 86.6%. On OSWorld-Verified, Qwen3.5 Medium leads at 58% vs Gemini 3.1 Flash-Lite at 54.3%. On CharXiv Reasoning, Qwen3.5 Medium leads at 77.2% vs Gemini 3.1 Flash-Lite at 73.2%. On MMMU-Pro, Qwen3.5 Medium leads at 76.9% vs Gemini 3.1 Flash-Lite at 76.8%.