Models/GLM-4.6

MDL

GLM-4.6

Z AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0.55 / $2.2

in / out

Context

200K

tokens

Avg score

56.1

10 benchmarks

AA Intelligence

28.7

index

Speed

49 tok/s

TTFT 0.6s

Released

Sep 30, 2025

About

GLM-4.6 is a open-weights model in the GLM family from Z AI. Benchmarked on 10 evals, averaging 56.1.

Benchmark scores · 10

avg 56.1 — higher is better

AIMEartificial-analysis · 2026-07

MMLU-Proartificial-analysis · 2026-07

82.9

GPQA Diamondartificial-analysis · 2026-07

τ²-benchartificial-analysis · 2026-07

70.5

LiveCodeBenchartificial-analysis · 2026-07

69.5

AA Long-Context Reasoningartificial-analysis · 2026-07

54.3

IFBenchartificial-analysis · 2026-07

43.4

SciCodeartificial-analysis · 2026-07

38.4

Terminal-Bench Hardartificial-analysis · 2026-07

Humanity's Last Examartificial-analysis · 2026-07

13.3

Details

PublisherZ AI

FamilyGLM

Parameters—

License—

WeightsOpen

ReleasedSep 30, 2025

Performance & price

Output speed49 tok/s

Latency (TTFT)0.6s

First answer42s

Price in / out$0.55 / $2.2 per 1M

Blended price$0.963 / 1M

Coding index45.8

Math index86.0

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$2.2/M