Key Takeaways
GLM 4.6V wins:
- Cheaper input tokens
- Cheaper output tokens
- Supports vision
GLM 4.7 wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
Price Advantage
GLM 4.6V
Benchmark Advantage
GLM 4.7
Context Window
GLM 4.7
Speed
GLM 4.7
Pricing Comparison
Price Comparison
| Metric | GLM 4.6V | GLM 4.7 | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.30 | $0.38 | GLM 4.6V |
| Output (per 1M tokens) | $0.90 | $1.75 | GLM 4.6V |
| Cache Read (per 1M) | $0.05 | $0.08 | GLM 4.6V |
Using a 3:1 input/output ratio, GLM 4.6V is 38% cheaper overall.
GLM 4.6V Providers
No provider data available
GLM 4.7 Providers
No provider data available
Benchmark Comparison
6
Benchmarks Compared
0
GLM 4.6V Wins
6
GLM 4.7 Wins
Benchmark Scores
| Benchmark | GLM 4.6V | GLM 4.7 | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 17.1 | 34.2 | |
Coding Index Code generation & understanding | 11.1 | 32.0 | |
Math Index Mathematical reasoning | 26.3 | 48.0 | |
MMLU Pro Academic knowledge | 75.2 | 79.4 | |
GPQA Graduate-level science | 56.6 | 66.4 | |
LiveCodeBench Competitive programming | 41.1 | 56.2 |
GLM 4.7 significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
GLM 4.6V
Other models
Context & Performance
Context Window
GLM 4.6V
131,072
tokens
GLM 4.7
202,752
tokens
GLM 4.7 has a 35% larger context window.
Speed Performance
| Metric | GLM 4.6V | GLM 4.7 | Winner |
|---|---|---|---|
| Tokens/second | 22.9 tok/s | 85.9 tok/s | |
| Time to First Token | 4.51s | 0.68s |
GLM 4.7 responds 275% faster on average.
Capabilities
Feature Comparison
| Feature | GLM 4.6V | GLM 4.7 |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | GLM 4.6V | GLM 4.7 |
|---|---|---|
| License | Open Source | Open Source |
| Author | Z-ai | Z-ai |
| Released | Dec 2025 | Dec 2025 |
GLM 4.6V Modalities
Input
imagetextvideo
Output
text
GLM 4.7 Modalities
Input
text
Output
text