MultimodalOpen weights

GLM 4.6V

Zhipu AI

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: Multimodal
Access: Open weights
Released: December 8, 2025
Context window: 131,072 tokens
Output speed: 44 tok/s
Latency (TTFT): 1.31s
Input: Image, Text, Video
Output: Text
API pricing: $0.30 in · $0.90 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

71.9

Coding

41.1

Math

85.3

General

MMLU-Pro	79.9
Humanity’s Last Exam	8.9

Compare GLM 4.6V with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all GLM 4.6V alternatives →