Z AI Models: Intelligence, Performance & Price
Artificial Analysis has benchmarked 23 models from Z AI. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Z AI is GLM-5.3 (max) at 45.
- For output speed, the fastest model is GLM-5.3 (max) at 91 t/s.
- For latency, GLM-5.3 (max) at 24.65s offers the lowest time to first answer token.
- For pricing, GLM 5.3 Flash at $0.25 offers the lowest cost per task. Prices vary up to 7.9x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All Z AI Releases
GLM 5.3 Flash
1 model
42
Highest Intelligence
GLM-5.3
2 models
45
Highest Intelligence
GLM-5.2
2 models
34
Highest Intelligence
GLM-5.1
2 models
26
Highest Intelligence
GLM 5V Turbo
1 model
23
Highest Intelligence
GLM-5-Turbo
1 model
27
Highest Intelligence
GLM-5
2 models
28
Highest Intelligence
GLM-4.7-Flash
2 models
15
Highest Intelligence
GLM-4.7
2 models
22
Highest Intelligence
GLM-4.6V
2 models
11
Highest Intelligence
GLM-4.6
2 models
19
Highest Intelligence
GLM-4.5V
2 models
8
Highest Intelligence
GLM-4.5
1 model
13
Highest Intelligence
GLM-4.5-Air
1 model
11
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| GLM-5.3 (max) | Z AI | 45 | 753B 40B active at inference time | 1M | $0.9 | 91 |   +17 | ||
| GLM 5.3 Flash | Z AI | 42 | 320B 18B active at inference time | 1M | $0.1 | 54 |  +16 | ||
| GLM-5.3 (low) | Z AI | 34 | 753B 40B active at inference time | 1M | $0.9 | 86 | | ||
| GLM-5.2 (max) | Z AI | 34 | 753B 40B active at inference time | 1M | $0.9 | 84 |   +15 | ||
| GLM-5 (Reasoning) | Z AI | 28 | 744B 40B active at inference time | 200k | $0.7 | 85 |   +3 | ||
| GLM-5-Turbo | Z AI | 27 | - | 200k | - | - | Not available | - | |
| GLM-5.1 (Reasoning) | Z AI | 26 | 744B 40B active at inference time | 200k | $0.8 | 77 |  +3 | ||
| GLM-5.1 (Non-reasoning) | Z AI | 24 | 744B 40B active at inference time | 200k | $0.9 | 71 | +2 | ||
| GLM 5V Turbo (Reasoning) | Z AI | 23 | - | 200k | - | - | Not available | - | |
| GLM-5.2 (Non-reasoning) | Z AI | 22 | 753B 40B active at inference time | 1M | $0.9 | 172 |   +4 | ||
| GLM-4.7 (Reasoning) | Z AI | 22 | 357B 32B active at inference time | 200k | $0.7 | 100 | +3 | ||
| GLM-5 (Non-reasoning) | Z AI | 22 | 744B 40B active at inference time | 200k | $0.7 | 79 | | ||
| GLM-4.6 (Reasoning) | Z AI | 19 | 357B 32B active at inference time | 200k | $0.4 | 36 |  | ||
| GLM-4.7 (Non-reasoning) | Z AI | 17 | 357B 32B active at inference time | 200k | $0.5 | 98 |  +3 | ||
| GLM-4.6 (Non-reasoning) | Z AI | 15 | 357B 32B active at inference time | 200k | $0.6 | 36 | | ||
| GLM-4.7-Flash (Reasoning) | Z AI | 15 | 31.2B 3B active at inference time | 200k | $0.1 | 73 | | ||
| GLM-4.5 (Reasoning) | Z AI | 13 | 355B 32B active at inference time | 128k | - | - | - | ||
| GLM-4.6V (Reasoning) | Z AI | 11 | 108B 12B active at inference time | 128k | $0.3 | 82 | | ||
| GLM-4.5-Air | Z AI | 11 | 106B 12B active at inference time | 128k | $0.3 | 74 | | ||
| GLM-4.7-Flash (Non-reasoning) | Z AI | 11 | 31.2B 3B active at inference time | 200k | $0.1 | 104 | | ||
| GLM-4.6V (Non-reasoning) | Z AI | 8 | 108B 12B active at inference time | 128k | $0.3 | 79 | | ||
| GLM-4.5V (Reasoning) | Z AI | 8 | 108B 12B active at inference time | 64k | $0.4 | 46 | | ||
| GLM-4.5V (Non-reasoning) | Z AI | 7 | 108B 12B active at inference time | 64k | $0.4 | 46 | |