Z AI
GLM-5.2 (max)
Quality Score54.9
Value Score40.8
Reliability52.2
Cache Discount81%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $1.40
- Output
- $4.40
- Cached Input
- $0.260
- Cached Output
- not available
- Cost per task
- $0.445
Capability
- Intelligence
- 52.6
- Coding
- 68.8
- Agentic
- 45.7
- Omniscience
- 4.4
- Correct
- 24.3%
- Blended price
- $0.902
Answer outcomes
Correct 24.3%Incorrect 19.9%Abstained 55.8%
Artificial Analysis benchmarks
- GDPval-AA v2
- 50%
- τ³-Banking
- 35%
- Terminal-Bench v2.1
- 78%
- SciCode
- 50%
- Humanity’s Last Exam
- 41%
- GPQA Diamond
- 89%
- CritPt
- 21%
- AA-Omniscience
- 52%
- AA-LCR
- 77%
Similar models
- GLM-5.3 (max)Z AIQuality Score 65.3Value Score 47.9
- GLM-5.2 (Non-reasoning)Z AIQuality Score 39.3Value Score 28.0
- DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeekQuality Score 55.1Value Score 50.5
- GPT-5.6 Luna (xhigh)OpenAIQuality Score 55.6Value Score 51.3
- GPT-5.6 Luna (max)OpenAIQuality Score 57.3Value Score 53.2
- Motif 3Motif TechnologiesQuality Score 54.4Value Score not available