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 Max

Models

Context window: 1,000,000 tokens^*
Maximum output: 131,072 tokens^*
Open weights: No^*
Reasoning: Yes^*

2026-08-02

WideSearch · version unreported · reported score · Qwen-Agent · Average item F1 over four runs#1^* · 81.90^*Platform unreported

ECI 157.4^*General capability index

alibaba

Qwen3.7 Max

Models

Context window: 1,000,000 tokens
Maximum output: 131,072 tokens
Open weights: No
Reasoning: Yes

2026-05-21

WideSearch · version unreported · reported score · Qwen-Agent · Average item F1 over four runs#2^* · 75.20^*Platform unreported

Radar · unrated0/4 core tests · not enough evidence

* Provisional data