Models/GLM-4.5V

MDL

GLM-4.5V

Z AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0.6 / $1.8

in / out

Context

65.5K

tokens

Avg score

37.1

10 benchmarks

AA Intelligence

9.1

index

Speed

62 tok/s

TTFT 1.1s

Released

Aug 11, 2025

About

GLM-4.5V is a open-weights model in the GLM family from Z AI. Benchmarked on 10 evals, averaging 37.1.

Benchmark scores · 10

avg 37.1 — higher is better

MMLU-Proartificial-analysis · 2026-07

78.8

AIMEartificial-analysis · 2026-07

GPQA Diamondartificial-analysis · 2026-07

68.4

LiveCodeBenchartificial-analysis · 2026-07

60.4

IFBenchartificial-analysis · 2026-07

34.2

τ²-benchartificial-analysis · 2026-07

22.5

SciCodeartificial-analysis · 2026-07

22.1

Humanity's Last Examartificial-analysis · 2026-07

5.9

Terminal-Bench Hardartificial-analysis · 2026-07

5.3

AA Long-Context Reasoningartificial-analysis · 2026-07

Details

PublisherZ AI

FamilyGLM

Parameters—

License—

WeightsOpen

ReleasedAug 11, 2025

Performance & price

Output speed62 tok/s

Latency (TTFT)1.1s

First answer34s

Price in / out$0.6 / $1.8 per 1M

Blended price$0.9 / 1M

Math index73.0

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$1.8/M