GLM-4.5-Air
GLM-4.5-Air is a more compact variant of GLM-4.5 designed for efficient Agentic, Reasoning, and Coding (ARC) applications. It features 106 billion total parameters with 12 billion active parameters using MoE architecture. Like GLM-4.5, it is a hybrid reasoning model providing thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses. Despite its compact design, GLM-4.5-Air delivers competitive performance with a score of 59.8 across 12 industry-standard benchmarks, ranking 6th overall while maintaining superior efficiency. It supports 128K context length and is released under MIT open-source license allowing commercial use.
GLM-4.5-Air is Z AI’s model designed for high-performance tasks. It processes at 106.41 tokens per second and is priced at $0.2 per million input tokens, targeting professional users.
When to Use GLM-4.5-Air
✓ Best For
- Complex mathematical computations.
- High-speed coding tasks.
- Data analysis requiring extensive context.
✗ Not Ideal For
- Applications requiring low latency.
- Basic conversational AI tasks.
How GLM-4.5-Air Compares
Intelligence Index · Higher is better
Benchmark Profile
Coding Index
Output Speed · tok/s
Math Index
Intelligence · Coding · Math
All Benchmark Scores (25)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 23.2 | |
| Coding Index | 23.8 | |
| Math Index | 80.7 | |
| MMLU-Pro | 815% | |
| GPQA | 733% | |
| LiveCodeBench | 684% | |
| HLE | 68% | |
| SWE-Bench Verified | 57.6% | |
| SciCode | 30.6% | |
| IFBench | 37.6% | |
| LCR | 43.7% | |
| TerminalBench Hard | 20.5% | |
| Tau2 | 46.5% | |
| AIME | 67.3% | |
| AIME 2025 | 80.7% | |
| MATH 500 | 96.5% | |
| AA-Index | 64.8% | |
| AIME 2024 | 89.4% | |
| BFCL-v3 | 76.4% | |
| BrowseComp | 21.3% | |
| Humanity's Last Exam | 10.6% | |
| MATH-500 | 98.1% | |
| TAU-bench Airline | 60.8% | |
| TAU-bench Retail | 77.9% | |
| Terminal-Bench | 30% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
