Z AI
GLM-4.6V (Reasoning)
GLM-4.6V series are Z.ai’s iterations in a multimodal large language model. GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales.
Z AI releasesModel Snapshot
TypeLanguage
ReleaseSep 30, 2025
Context128,000
Tagsvision, file-input, reasoning, tool-use
Overall
Rank #212 across 526
23.4
Coding
Rank #215 across 436
19.7
Blended Price
Rank #129 across 357
$0.450/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed44.9 tok/s
First Token1.32s
Max Output24,000
Pricing
Blended$0.450/M
Input$0.300/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 23.4 | #212 |
| Artificial Analysis Coding Index | coding | 19.7 | #215 |
| Artificial Analysis Math Index | math | 85.3 | #45 |
| MMLU-Pro | reasoning | 79.9% | #116 |