Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GLM-4.5-Air
Z.AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GLM-4.5-Air Z.AI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 11.1 | 11.1 | |
| Coding | — | 22.4 | |
| Math | 80.7 | — | |
| Agentic | — | 1.3 | |
| Speed | 73.7 t/s | Best: 118 t/s | |
| TTFT | 2.42 s | Best: 0.85 s | |
| Input · $ / 1M tokens | $0.17×2.8 relative to the lowest price among the compared models | Best: $0.060 | |
| Output · $ / 1M tokens | $0.98×3.9 relative to the lowest price among the compared models | Best: $0.25 | |
| Context window | 128K | Best: 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0236 |
Intelligence
- GLM-4.5-Air
- 11.1
- Granite 4.2 8B
- 11.1
Coding
- GLM-4.5-Air
- —
- Granite 4.2 8B
- 22.4
Math
- GLM-4.5-Air
- 80.7
- Granite 4.2 8B
- —
Agentic
- GLM-4.5-Air
- —
- Granite 4.2 8B
- 1.3
Speed
- GLM-4.5-Air
- 73.7 t/s
- Granite 4.2 8B
- Best: 118 t/s
TTFT
- GLM-4.5-Air
- 2.42 s
- Granite 4.2 8B
- Best: 0.85 s
Input · $ / 1M tokens
- GLM-4.5-Air
- $0.17×2.8 relative to the lowest price among the compared models
- Granite 4.2 8B
- Best: $0.060
Output · $ / 1M tokens
- GLM-4.5-Air
- $0.98×3.9 relative to the lowest price among the compared models
- Granite 4.2 8B
- Best: $0.25
Context window
- GLM-4.5-Air
- 128K
- Granite 4.2 8B
- Best: 131K
Reasoning
- GLM-4.5-Air
- Yes
- Granite 4.2 8B
- Yes
Open weights
- GLM-4.5-Air
- Yes
- Granite 4.2 8B
- Yes
Cost / task
- GLM-4.5-Air
- —
- Granite 4.2 8B
- $0.0236
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- GLM-4.5-Air11.1 · $0.372
- Granite 4.2 8B11.1 · $0.107