Comparing 2 models

MiMo-V2.5-Pro vs GLM 5.1

Facts first, then task-specific rankings. A highlighted cell is better only for that row, not universally.

metric

Best for

Best Open-Weight LLM for Self-Hosting (#2)

Best Open-Weight LLM for Self-Hosting (#3)

Provider

xiaomi

z-ai

Context

1.1MBest

205K

Input / 1M

$0.43Best

$0.97

Output / 1M

$0.87Best

$3.04

Tool use

yesBest

Vision

—

Reasoning

yesBest

Open-weight

yesBest

Released

Apr 22, 2026

Jan 20, 2025

task evidence

How they place when the question changes

Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.