GeekRadar / The comparison desk

COMPARE.

AI

Filters

Filter AI models

Rank by benchmark Clear all filters

Best result per entry; configurations may differ.

alibaba

Qwen 3.8 27B

Models

Context window: 262,144 tokens^*
Maximum output: 32,768 tokens^*
Open weights: Yes^*
Reasoning: Yes^*

2026-08-14

Visual math problem solving MathVision · version unreported · reported score · Code interpreter disabled#1^* · 90^*Platform unreported

ECI 152.7^*General capability index

* Provisional data