The Known Good Updated 25 Jul 2026
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.2 ·Moonshot AI vs Z.ai

MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.2 — head-to-head comparison

MoonshotAI: Kimi K2.6 profile Z.ai: GLM 5.2 profile All comparisons
MoonshotAI: Kimi K2.6 — Moonshot AI
Quality
#7 of 61
93based on 3 of 6 evaluations
Known Good Index
Speed
#112 of 316
66.0
Output tokens per second
Price
#211 of 340
$1.16
Blended per 1M tokens
In $0.65 · Out $2.72
Cache hit price
#99 of 206
$0.11
per 1M tokens (−83%)
Context
#172 of 345
262k
tokens (~400 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, MoonshotAI: Kimi K2.6 scores 93 and Z.ai: GLM 5.2 scores 91 — a 2-point lead for MoonshotAI: Kimi K2.6. They share 3 published evaluations, with MoonshotAI: Kimi K2.6 ahead on 1 and Z.ai: GLM 5.2 ahead on 2.

Blended pricing is $1.16 per 1M tokens for MoonshotAI: Kimi K2.6 and $1.12 for Z.ai: GLM 5.2, within 10% of each other.

Throughput is 66 tokens per second for MoonshotAI: Kimi K2.6 and 55 for Z.ai: GLM 5.2, with time to first token at 1.1s and 1.7s. MoonshotAI: Kimi K2.6 accepts 262k tokens of context against 1.05M.

MoonshotAI: Kimi K2.6 is open weights under Open weights (unrestricted); Z.ai: GLM 5.2 is open weights under Open weights (unrestricted). 32 tracked hosts serve one or both, and 18 serve both.

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

At a glance
MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Known Good Index 93 based on 3 of 6 evaluations 91 based on 3 of 6 evaluations
Blended $/1M $1.16 $1.12
Output tok/s 66 55
Context window 262k 1.05M
Providers 21 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.

MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Known Good Index 93 91
Mathematics Index 96 86
Science Index 95 97
Agentic Index 87 91
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = MoonshotAI: Kimi K2.6 · marker = Z.ai: GLM 5.2 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond91 / 92
MATH / AIME96 / 86
SWE-bench Verified77 / 79

Right-hand figures read MoonshotAI: Kimi K2.6 / Z.ai: GLM 5.2. MoonshotAI: Kimi K2.6 leads on 1 of 3, 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.

MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Text Arena 1,455 1,464
Text Arena (style controlled) 1,461 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.

MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Input $/1M $0.65 $0.73
Output $/1M $2.72 $2.28
Blended $/1M $1.16 $1.12
Cache read $/1M $0.109 $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.

MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Context window 262k 1.05M
Max output tokens 262k 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.

MetricMoonshotAI: Kimi K2.6Z.ai: GLM 5.2
Output tokens/s 66 55
Time to first token 1.1s 1.7s
The Known Good

Providers

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

32 hosts · 18 serve both
Full provider benchmarks →
Provider MoonshotAI: Kimi K2.6 blendedMoonshotAI: Kimi K2.6 tok/s Z.ai: GLM 5.2 blendedZ.ai: GLM 5.2 tok/s
CoreWeave $1.34 239 $1.18 181
Together $2.02 166 $2.15 47
Decart $1.35 129 $1.52 60
Fireworks $1.71 111 $2.15 65
ModelRun $1.38 110 — —
DeepInfra $1.44 65 $1.45 49
Crusoe $1.40 63 — —
Venice $1.44 63 $2.15 39
Cloudflare $1.71 56 $2.15 74
DigitalOcean $1.37 52 $1.89 13
Chutes $1.37 47 $1.93 56
SiliconFlow $1.43 47 $2.00 48
Phala $1.97 46 $2.15 46
Parasail $1.44 45 $2.15 56
Inceptron $1.30 37 $1.43 29
Moonshot AI · first party $1.71 37 — —
Novita $1.45 36 $1.12 37
StreamLake $1.54 36 $1.11 37
Baidu · first party $1.16 33 $1.12 40
AtlasCloud $1.71 32 $1.94 38
BaseTen $1.71 — $2.15 119
Wafer — — $2.15 103
Ionstream — — $2.15 101
Friendli — — $2.15 80
Alibaba · first party — — $1.27 69
Z.AI · first party — — $2.15 49
AkashML — — $1.18 46
Morph — — $1.85 43
GMICloud — — $1.42 39
Io Net — — $4.40 29
Sail Research — — $1.72 20
Ambient — — $1.89 14

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 →