Model Comparison
GLM-4.5-Air
vs. GLM-4.6V (Non-reasoning)
Comparing 2 AI models · 12 benchmarks · Z AI
Recommended Pick
Z GLM-4.5-Air 17 metric wins Strongest on: Value, Input price, Blended price
Best Value
GLM-4.5-Air
100.0 value score
60.3 reasoning / $0.37/1M
Lowest Price
GLM-4.5-Air
$0.17/1M input price
Best Reasoning
GLM-4.5-Air
60.3 reasoning score
Blends available reasoning benchmarks
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
GLM-4.5-Air has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
GLM-4.5-Air is 1.8x cheaper on input tokens than GLM-4.6V (Non-reasoning).
Speed gap
GLM-4.5-Air generates about 1.3x as many tokens per second as GLM-4.6V (Non-reasoning).
Reasoning gap
GLM-4.5-Air leads GLM-4.6V (Non-reasoning) by 35.5 points on reasoning.
Top-pick rationale
GLM-4.5-Air wins 17 measurable categories, including Value, Input price, Blended price, Throughput.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
GLM-4.5-Air
Z AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
GLM-4.6V (Non-reasoning)
Z AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Z GLM-4.5-Air | Z GLM-4.6V (Non-reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.17/1M | $0.30/1M |
| Output Cost | $0.98/1M | $0.90/1M |
| Blended (3:1) | $0.37/1M | $0.45/1M |
| Specifications | ||
| Organization | Z AI | Z AI |
| Release Date | Jul 28, 2025 | Dec 8, 2025 |
| Performance & Speed | ||
| Throughput | 86.2 tok/s | 68.4 tok/s |
| TTFT | 1538ms | 1190ms |
| Latency | 24749ms | 1190ms |
| Composite Indices | ||
| Value Score | 100.0 | 34.0 |
| Reasoning Score | 60.3 | 24.8 |
| Intelligence | 16.5 | 11.0 |
| Math | 80.7 | 26.3 |
| Standard Benchmarks | ||
| GPQA | 73.3% | 56.6% |
| MMLU Pro | 81.5% | 75.2% |
| HLE | 6.8% | 3.7% |
| LiveCodeBench | 68.4% | 41.1% |
| MATH 500 | 96.5% | — |
| AIME 2025 | 80.7% | 26.3% |
| AIME (Original) | 67.3% | — |
| SciCode | 30.6% | 27.2% |
| LCR | 43.7% | 12.3% |
| IFBench | 37.6% | 27.9% |
| TAU-bench v2 | 46.5% | 30.7% |
| TerminalBench Hard | 20.5% | 3.0% |
Key Takeaways
GLM-4.5-Air offers the best value at $0.17/1M, making it ideal for high-volume applications and cost-conscious projects.
GLM-4.5-Air has the strongest reasoning profile with a 60.3 reasoning score, combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
GLM-4.5-Air
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
GLM-4.6V (Non-reasoning)
- General-purpose AI
- Versatile applications
