The Known Good Updated 8 Oct 2026 Subscribe
Qwen: Qwen3.7 Max vs Z.ai: GLM 4.7 ·Alibaba vs Z.ai

Qwen: Qwen3.7 Max vs Z.ai: GLM 4.7 — head-to-head comparison

Qwen: Qwen3.7 Max profile Z.ai: GLM 4.7 profile All comparisons
Qwen: Qwen3.7 Max — Alibaba
Quality
#6 of 65
93based on 3 of 7 evaluations
Known Good Index
Speed
#132 of 356
78.4
Output tokens per second
Price
#356 of 504
$2.21
Blended per 1M tokens
In $1.48 · Out $4.42
Cache hit price
#328 of 384
$0.29
per 1M tokens (−80%)
Context
#187 of 550
1.00M
tokens (~1,500 pages)
Z.ai: GLM 4.7 — Z.ai
Quality
#30 of 65
69based on 3 of 7 evaluations
Known Good Index
Speed
#282 of 356
40.2
Output tokens per second
Price
#274 of 504
$1.00
Blended per 1M tokens
In $0.60 · Out $2.20
Cache hit price
#219 of 384
$0.11
per 1M tokens (−82%)
Context
#362 of 550
205k
tokens (~300 pages)
Summary

On the Known Good Index, Qwen: Qwen3.7 Max scores 93 and Z.ai: GLM 4.7 scores 69 — a 24-point lead for Qwen: Qwen3.7 Max. They share 2 published evaluations, with Qwen: Qwen3.7 Max ahead on 2 and Z.ai: GLM 4.7 ahead on 0.

Blended pricing is $2.21 per 1M tokens for Qwen: Qwen3.7 Max and $1.00 for Z.ai: GLM 4.7 — Z.ai: GLM 4.7 is about 2.2× cheaper.

Throughput is 78 tokens per second for Qwen: Qwen3.7 Max and 40 for Z.ai: GLM 4.7, with time to first token at 1.0s and 3.2s. Qwen: Qwen3.7 Max accepts 1.00M tokens of context against 205k.

Qwen: Qwen3.7 Max is proprietary; Z.ai: GLM 4.7 is open weights under Open weights (unrestricted). 11 tracked hosts serve one or both, and 1 serve both.

Generated from tracked data on 8 Oct 2026 · how these comparisons are computed →

At a glance
MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Known Good Index 93 based on 3 of 7 evaluations 69 based on 3 of 7 evaluations
Blended $/1M $2.21 $1.00
Output tok/s 78 40
Context window 1.00M 205k
Providers 2 10
Jump to section

Quality

Known Good Index and the capability indices, side by side

Index scores

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

MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Known Good Index 93 69
Openness Index 5 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Qwen: Qwen3.7 Max · marker = Z.ai: GLM 4.7 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond91 / 83
Mock AIME 2024–2596 / 83

Right-hand figures read Qwen: Qwen3.7 Max / Z.ai: GLM 4.7. Qwen: Qwen3.7 Max leads on 2 of 2, Z.ai: GLM 4.7 on 0.

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.

MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Text Arena — 1,436
Text Arena (style controlled) — 1,442
The Known Good

Price & Cost

Published API pricing by token type

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.

MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Input $/1M $1.48 $0.60
Output $/1M $4.42 $2.20
Blended $/1M $2.21 $1.00
Cache read $/1M $0.295 $0.110
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.

MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Context window 1.00M 205k
Max output tokens 131k 131k
The Known Good

Speed & Latency

Mean throughput and time to first token across hosting providers, over successful measurements from the last 48 hours

Throughput and latency

Means across all tracked providers over successful measurements from the last 48 hours, derived from OpenRouter endpoint telemetry.

MetricQwen: Qwen3.7 MaxZ.ai: GLM 4.7
Output tokens/s 78 40
Time to first token 1.0s 3.2s
The Known Good

Providers

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

11 hosts · 1 serve both
Full provider benchmarks →
Provider Qwen: Qwen3.7 Max blendedQwen: Qwen3.7 Max tok/s Z.ai: GLM 4.7 blendedZ.ai: GLM 4.7 tok/s
Alibaba · first party $2.21 88 — —
AtlasCloud $3.75 33 $0.85 62
Cerebras — — $2.38 252
Google · first party — — $1.00 126
StreamLake — — $0.80 34
Phala — — $1.46 31
Z.AI · first party — — $1.00 26
Novita — — $0.90 24
DeepInfra — — $0.74 16
Venice — — $0.78 16
Mancer 2 — — $1.15 15

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 →