Compare AI models

Specifications
Parameters
—2.4T
Context window
1M262k
Benchmarks
Terminal-Bench 2.1
85.8%76.03%
Overview
CompanyGoogleQwen
Release dateAug 13 2026Aug 12 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.7 Flash leads Qwen3.8-2.4T-A95B on 1 of the 1 benchmark they both report (Terminal-Bench 2.1). Qwen3.8-2.4T-A95B shipped 1 day before Gemini 3.7 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.7 Flash) vs 262k (Qwen3.8-2.4T-A95B). Gemini 3.7 Flash is closed, while Qwen3.8-2.4T-A95B is open weight.

On Terminal-Bench 2.1, Gemini 3.7 Flash leads at 85.8% vs Qwen3.8-2.4T-A95B at 76.03%.