Loading...
Loading...
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.
Quality Index
30.2
101st of 442
Top 23%
Coding Index
30.2
79th of 352
Top 23%
Math Index
44.3
148th of 268
Top 55%
Price/1M
$1.00
482nd cheapest
223% above median
Top 72%
Speed
100 tok/s
Top 28%
TTFT
1.36s
Context Window
205K
103rd largest
Top 30%
Input
$0.60
per 1M tokens
Output
$2.20
per 1M tokens
Blended
$1.00
per 1M tokens
Cheaper than 28% of models. Median price is $0.31/1M tokens.
Daily
$1.00
Monthly
$30.00
100
tokens/sec
Faster than 72% of models
1.36
seconds
Faster than 20% of models
1.36
seconds
Faster than 32% of models
Market Median
46 tok/s
120% faster
Median TTFT
0.42s
225% slower
Throughput/Dollar
100
tok/s per $/1M
Speed Comparison
Context Window
205K
tokens
Larger than 70% of models
Max Output
205K
tokens
100% of context