Compare AI models

Specifications
Parameters
27B/35B/122B320B
Context window
256k1M
API pricing
Cheapest input
—$0.0399Relace
Cheapest output
—$0.0784Relace
—$11.90Relace · fp4
Benchmarks
Humanity's Last Exam · with tools
47.5%55.3%
Overview
CompanyQwenZ.ai
Release dateFeb 24 2026Aug 26 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-5.3-Flash leads Qwen3.5 Medium on 1 of the 1 benchmark they both report (Humanity's Last Exam). Qwen3.5 Medium shipped 183 days before GLM-5.3-Flash, so benchmark comparisons should account for the intervening progress.

Qwen3.5 Medium has 27B/35B/122B parameters, while GLM-5.3-Flash has 320B. Context windows are 256k (Qwen3.5 Medium) vs 1M (GLM-5.3-Flash).

On Humanity's Last Exam · with tools, GLM-5.3-Flash leads at 55.3% vs Qwen3.5 Medium at 47.5%.