The Known Good Updated 25 Jul 2026
Z.ai: GLM 4.7 vs Z.ai: GLM 5.2 ·Z.ai vs Z.ai

Z.ai: GLM 4.7 vs Z.ai: GLM 5.2 — head-to-head comparison

Z.ai: GLM 4.7 profile Z.ai: GLM 5.2 profile All comparisons
Z.ai: GLM 4.7 — Z.ai
Quality
#26 of 61
68based on 3 of 6 evaluations
Known Good Index
Speed
#111 of 316
66.0
Output tokens per second
Price
#168 of 340
$0.74
Blended per 1M tokens
In $0.40 · Out $1.75
Cache hit price
#83 of 206
$0.080
per 1M tokens (−80%)
Context
#193 of 345
205k
tokens (~300 pages)
Z.ai: GLM 5.2 — Z.ai
Quality
#8 of 61
91based on 3 of 6 evaluations
Known Good Index
Speed
#147 of 316
55.2
Output tokens per second
Price
#204 of 340
$1.12
Blended per 1M tokens
In $0.73 · Out $2.28
Cache hit price
#116 of 206
$0.13
per 1M tokens (−81%)
Context
#45 of 345
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, Z.ai: GLM 4.7 scores 68 and Z.ai: GLM 5.2 scores 91 — a 23-point lead for Z.ai: GLM 5.2. They share 2 published evaluations, with Z.ai: GLM 4.7 ahead on 0 and Z.ai: GLM 5.2 ahead on 2.

Blended pricing is $0.74 per 1M tokens for Z.ai: GLM 4.7 and $1.12 for Z.ai: GLM 5.2 — Z.ai: GLM 4.7 is about 1.5× cheaper.

Throughput is 66 tokens per second for Z.ai: GLM 4.7 and 55 for Z.ai: GLM 5.2, with time to first token at 2.1s and 1.7s. Z.ai: GLM 4.7 accepts 205k tokens of context against 1.05M.

Z.ai: GLM 4.7 is open weights under Open weights (unrestricted); Z.ai: GLM 5.2 is open weights under Open weights (unrestricted). 31 tracked hosts serve one or both, and 7 serve both.

Generated from tracked data on 26 Jul 2026 · how these comparisons are computed →

At a glance
MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Known Good Index 68 based on 3 of 6 evaluations 91 based on 3 of 6 evaluations
Blended $/1M $0.74 $1.12
Output tok/s 66 55
Context window 205k 1.05M
Providers 9 29
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Known Good Index 68 91
Mathematics Index 83 86
Science Index 86 97
Agentic Index 35 91
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Z.ai: GLM 4.7 · marker = Z.ai: GLM 5.2 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond83 / 92
MATH / AIME83 / 86

Right-hand figures read Z.ai: GLM 4.7 / Z.ai: GLM 5.2. Z.ai: GLM 4.7 leads on 0 of 2, Z.ai: GLM 5.2 on 2.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Text Arena 1,436 1,464
Text Arena (style controlled) 1,442 1,469
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Input $/1M $0.40 $0.73
Output $/1M $1.75 $2.28
Blended $/1M $0.74 $1.12
Cache read $/1M $0.080 $0.135
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Context window 205k 1.05M
Max output tokens 131k 131k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricZ.ai: GLM 4.7Z.ai: GLM 5.2
Output tokens/s 66 55
Time to first token 2.1s 1.7s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

31 hosts · 7 serve both
Full provider benchmarks →
Provider Z.ai: GLM 4.7 blendedZ.ai: GLM 4.7 tok/s Z.ai: GLM 5.2 blendedZ.ai: GLM 5.2 tok/s
Google · first party $1.00 147 — —
Cerebras $2.38 132 — —
DeepInfra $0.74 49 $1.45 49
Venice $1.07 49 $2.15 39
AtlasCloud $0.85 47 $1.94 38
StreamLake $0.80 37 $1.11 37
Z.AI · first party $1.00 33 $2.15 49
Phala $1.46 30 $2.15 46
Novita $0.90 29 $1.12 37
CoreWeave — — $1.18 181
BaseTen — — $2.15 119
Wafer — — $2.15 103
Ionstream — — $2.15 101
Friendli — — $2.15 80
Cloudflare — — $2.15 74
Alibaba · first party — — $1.27 69
Fireworks — — $2.15 65
Decart — — $1.52 60
Chutes — — $1.93 56
Parasail — — $2.15 56
SiliconFlow — — $2.00 48
Together — — $2.15 47
AkashML — — $1.18 46
Morph — — $1.85 43
Baidu · first party — — $1.12 40
GMICloud — — $1.42 39
Inceptron — — $1.43 29
Io Net — — $4.40 29
Sail Research — — $1.72 20
Ambient — — $1.89 14
DigitalOcean — — $1.89 13

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →