Model comparison
GLM-4.6V vs GLM-4.5V
- Input
- $0.30
- Output
- $0.90
- Context
- 128K
- Released
- 2025-12-08
- Input
- $0.60 / 1M tokens
- Output
- $1.80 / 1M tokens
- Context
- 64K
- Released
- 2025-08-11
GLM-4.6V scores higher on 3 of the 5 benchmarks both models report (the other leads on 1); GLM-4.6V is cheaper on input tokens ($0.3 vs $0.6 per 1M, 2×); GLM-4.6V has the larger context window (128K vs 64K).
Specs and pricing side by side
| Spec | GLM-4.6V | GLM-4.5V |
|---|---|---|
| Maker | Z.ai (Zhipu / GLM) | Z.ai (Zhipu / GLM)same |
| Released | 2025-12-08 | 2025-08-11 |
| Context window | 128K | 64K |
| Max output | Not disclosed | 16K |
| Input price | $0.30 | $0.60 / 1M tokens |
| Output price | $0.90 | $1.80 / 1M tokens |
| Parameters | 106B total / ~12B active (MoE) | 106B total / 12B active (MoE) |
| License | MIT | MITsame |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision, Video, PDF | Text, Vision, Video, PDFsame |
| Knowledge cutoff | Not disclosed | December 2024 |
Benchmarks both models report
| Benchmark | GLM-4.6V | GLM-4.5V |
|---|---|---|
| MMBench V1.1 | 88.8% | 88.2% |
| MathVista | 85.2% | 84.6% |
| AI2D | 88.8% | 88.1% |
| OCRBench | 86.5% | 86.5% |
| WebVoyager | 81% | 84.4% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick GLM-4.6V if…
- You care about MMBench V1.1, MathVista, AI2D (it scores higher on 3 shared benchmarks).
- Cost matters: input tokens cost 2× less ($0.3 vs $0.6 per 1M).
- You need the longer context (128K vs 64K).
- Your use case is: multimodal agents and GUI automation that act on what they see (WebVoyager-style web navigation).
Pick GLM-4.5V if…
- You care about WebVoyager (it scores higher on 1 shared benchmark).
- Your use case is: document, chart and long-PDF understanding and information extraction.
FAQ
Which is better, GLM-4.6V or GLM-4.5V?
GLM-4.6V scores higher on 3 of the 5 benchmarks both models report (the other leads on 1); GLM-4.6V is cheaper on input tokens ($0.3 vs $0.6 per 1M, 2×); GLM-4.6V has the larger context window (128K vs 64K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is GLM-4.6V?
GLM-4.6V: $0.30 input, $0.90 output. GLM-4.5V: $0.60 / 1M tokens input, $1.80 / 1M tokens output (list API prices as published by each maker).
What are the context windows of GLM-4.6V and GLM-4.5V?
GLM-4.6V offers 128K with up to Not disclosed output; GLM-4.5V offers 64K with up to 16K output.
Is GLM-4.6V newer than GLM-4.5V?
GLM-4.6V was released 2025-12-08; GLM-4.5V was released 2025-08-11.