The Known Good Updated 25 Jul 2026
Z.ai: GLM 5 vs Z.ai: GLM 5.2 ·Z.ai vs Z.ai

Z.ai: GLM 5 vs Z.ai: GLM 5.2 — head-to-head comparison

Z.ai: GLM 5 profile Z.ai: GLM 5.2 profile All comparisons
Z.ai: GLM 5 — Z.ai
Quality
#19 of 61
77based on 4 of 6 evaluations
Known Good Index
Speed
#214 of 316
37.3
Output tokens per second
Price
#217 of 340
$1.35
Blended per 1M tokens
In $0.95 · Out $2.55
Cache hit price
#138 of 206
$0.20
per 1M tokens (−79%)
Context
#189 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
$1.07
Blended per 1M tokens
In $0.70 · Out $2.20
Cache hit price
#115 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 5 scores 77 and Z.ai: GLM 5.2 scores 91 — a 15-point lead for Z.ai: GLM 5.2. They share 3 published evaluations, with Z.ai: GLM 5 ahead on 0 and Z.ai: GLM 5.2 ahead on 3.

Blended pricing is $1.35 per 1M tokens for Z.ai: GLM 5 and $1.07 for Z.ai: GLM 5.2 — Z.ai: GLM 5.2 is about 1.3× cheaper.

Throughput is 37 tokens per second for Z.ai: GLM 5 and 55 for Z.ai: GLM 5.2, with time to first token at 2.5s and 1.7s. Z.ai: GLM 5 accepts 205k tokens of context against 1.05M.

Z.ai: GLM 5 is open weights under Open weights (unrestricted); Z.ai: GLM 5.2 is open weights under Open weights (unrestricted). 30 tracked hosts serve one or both, and 13 serve both.

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

At a glance
MetricZ.ai: GLM 5Z.ai: GLM 5.2
Known Good Index 77 based on 4 of 6 evaluations 91 based on 3 of 6 evaluations
Blended $/1M $1.35 $1.07
Output tok/s 37 55
Context window 205k 1.05M
Providers 14 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 5Z.ai: GLM 5.2
Known Good Index 77 91
Coding Index 67 —
Mathematics Index 80 86
Science Index 92 97
Agentic Index 67 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 5 · marker = Z.ai: GLM 5.2 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond88 / 92
MATH / AIME80 / 86
SWE-bench Verified72 / 79

Right-hand figures read Z.ai: GLM 5 / Z.ai: GLM 5.2. Z.ai: GLM 5 leads on 0 of 3, Z.ai: GLM 5.2 on 3.

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 5Z.ai: GLM 5.2
Text Arena 1,445 1,464
Text Arena (style controlled) 1,457 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 5Z.ai: GLM 5.2
Input $/1M $0.95 $0.70
Output $/1M $2.55 $2.20
Blended $/1M $1.35 $1.07
Cache read $/1M $0.200 $0.130
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 5Z.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 5Z.ai: GLM 5.2
Output tokens/s 37 55
Time to first token 2.5s 1.7s
The Known Good

Providers

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

30 hosts · 13 serve both
Full provider benchmarks →
Provider Z.ai: GLM 5 blendedZ.ai: GLM 5 tok/s Z.ai: GLM 5.2 blendedZ.ai: GLM 5.2 tok/s
Amazon Bedrock · first party $1.55 109 — —
GMICloud $0.93 69 $1.42 50
Chutes $1.35 48 $1.93 57
Baidu · first party $1.08 43 $1.12 42
Parasail $1.55 42 $2.15 45
Phala $1.77 38 $2.15 48
Novita $1.55 36 $1.07 39
StreamLake $0.93 35 $1.07 45
Z.AI · first party $1.55 33 $2.15 49
Venice $1.55 32 $2.15 56
DeepInfra $0.97 29 $1.45 68
SiliconFlow $1.35 29 $2.00 49
AtlasCloud $1.50 26 $1.94 34
DigitalOcean $1.16 8 $1.89 23
Friendli — — $2.15 124
Fireworks — — $2.15 123
BaseTen — — $2.15 120
Ionstream — — $2.15 108
Wafer — — $2.15 108
Cloudflare — — $2.15 84
Ambient — — $1.89 78
Decart — — $1.52 71
Alibaba · first party — — $1.27 65
Together — — $2.15 62
Morph — — $1.85 52
CoreWeave — — $1.18 49
Inceptron — — $1.43 34
AkashML — — $1.18 33
Io Net — — $4.40 28
Sail Research — — $1.72 27

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 →