Models/GLM-4.6V

MDL

GLM-4.6V

Z AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0.3 / $0.9

in / out

Context

131.1K

tokens

Avg score

40.9

10 benchmarks

AA Intelligence

16.8

index

Speed

55 tok/s

TTFT 1.1s

Released

Dec 8, 2025

About

GLM-4.6V is a open-weights model in the GLM family from Z AI. Benchmarked on 10 evals, averaging 40.9.

Benchmark scores · 10

avg 40.9 — higher is better

AIMEartificial-analysis · 2026-07

85.3

MMLU-Proartificial-analysis · 2026-07

79.9

GPQA Diamondartificial-analysis · 2026-07

71.9

AA Long-Context Reasoningartificial-analysis · 2026-07

40.3

τ²-benchartificial-analysis · 2026-07

31.6

SciCodeartificial-analysis · 2026-07

30.4

IFBenchartificial-analysis · 2026-07

30.1

LiveCodeBenchartificial-analysis · 2026-07

Terminal-Bench Hardartificial-analysis · 2026-07

14.4

Humanity's Last Examartificial-analysis · 2026-07

8.9

Details

PublisherZ AI

FamilyGLM

Parameters—

License—

WeightsOpen

ReleasedDec 8, 2025

Performance & price

Output speed55 tok/s

Latency (TTFT)1.1s

First answer38s

Price in / out$0.3 / $0.9 per 1M

Blended price$0.45 / 1M

Math index85.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0.9/M