MMODELYST
Models/GLM-5.2 (max)
MDL

GLM-5.2 (max)

Z AI

Verified against Artificial Analysis · Jul 27, 2026
Capability
96
percentile index
Price /M
$1.4 / $4.4
in / out
Context
Avg score
67.8
7 benchmarks
AA Intelligence
51.1
index
Speed
157 tok/s
TTFT 0.9s
Released
Jun 16, 2026
About

GLM-5.2 (max) is a open-weights model in the GLM family from Z AI. Benchmarked on 7 evals, averaging 67.8.

Benchmark scores · 7
avg 67.8 — higher is better
τ²-bench
99.1
GPQA Diamond
89.5
IFBench
73.3
AA Long-Context Reasoning
71.3
Terminal-Bench Hard
50.8
SciCode
50.5
Humanity's Last Exam
40.1
Details
PublisherZ AI
FamilyGLM
Parameters
License
WeightsOpen
ReleasedJun 16, 2026
Performance & price
Output speed157 tok/s
Latency (TTFT)0.9s
First answer14s
Price in / out$1.4 / $4.4 per 1M
Blended price$2.15 / 1M
Coding index68.8

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

Capability over time
GPQA Diamondfirst seen at 89.5
1mo ago
Humanity's Last Examfirst seen at 40.1
1mo ago
SciCodefirst seen at 50.5
1mo ago
IFBenchfirst seen at 73.3
1mo ago
τ²-benchfirst seen at 99.1
1mo ago
Terminal-Bench Hardfirst seen at 50.8
1mo ago

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

API providers
Artificial Analysis$4.4/M