Key Takeaways
Kimi K2 Thinking wins:
- No clear advantages in compared metrics
GLM 4.6V wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Supports vision
Price Advantage
GLM 4.6V
Benchmark Advantage
GLM 4.6V
Context Window
GLM 4.6V
Speed
GLM 4.6V
Pricing Comparison
Price Comparison
| Metric | Kimi K2 Thinking | GLM 4.6V | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.47 | $0.30 | GLM 4.6V |
| Output (per 1M tokens) | $2.00 | $0.90 | GLM 4.6V |
| Cache Read (per 1M) | $0.14 | $0.05 | GLM 4.6V |
Using a 3:1 input/output ratio, GLM 4.6V is 47% cheaper overall.
Kimi K2 Thinking Providers
No provider data available
GLM 4.6V Providers
No provider data available
Benchmark Comparison
6
Benchmarks Compared
0
Kimi K2 Thinking Wins
0
GLM 4.6V Wins
Benchmark Scores
| Benchmark | Kimi K2 Thinking | GLM 4.6V | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | - | 17.1 | - |
Coding Index Code generation & understanding | - | 11.1 | - |
Math Index Mathematical reasoning | - | 26.3 | - |
MMLU Pro Academic knowledge | - | 75.2 | - |
GPQA Graduate-level science | - | 56.6 | - |
LiveCodeBench Competitive programming | - | 41.1 | - |
GLM 4.6V significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Kimi K2 Thinking
Other models
Context & Performance
Context Window
Kimi K2 Thinking
131,072
tokens
GLM 4.6V
131,072
tokens
Speed Performance
| Metric | Kimi K2 Thinking | GLM 4.6V | Winner |
|---|---|---|---|
| Tokens/second | N/A | 22.9 tok/s | |
| Time to First Token | N/A | 4.51s |
Capabilities
Feature Comparison
| Feature | Kimi K2 Thinking | GLM 4.6V |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Kimi K2 Thinking | GLM 4.6V |
|---|---|---|
| License | Open Source | Open Source |
| Author | Moonshotai | Z-ai |
| Released | Nov 2025 | Dec 2025 |
Kimi K2 Thinking Modalities
Input
text
Output
text
GLM 4.6V Modalities
Input
imagetextvideo
Output
text