Model Comparator
Compare up to four models using the same criteria.
2 models compared
- INTELLECT-3 (Based on GLM-4.5-Air)
Prime Intellect
- GPT-5 (ChatGPT)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | INTELLECT-3 (Based on GLM-4.5-Air) Prime Intellect | GPT-5 (ChatGPT) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 10.6 | 10.4 | |
| Math | Best: 88 | 48.3 | |
| Context window | Best: 131K | 128K | |
| Reasoning | Yes | No | |
| Open weights | Yes | No |
Intelligence
- INTELLECT-3 (Based on GLM-4.5-Air)
- Best: 10.6
- GPT-5 (ChatGPT)
- 10.4
Math
- INTELLECT-3 (Based on GLM-4.5-Air)
- Best: 88
- GPT-5 (ChatGPT)
- 48.3
Context window
- INTELLECT-3 (Based on GLM-4.5-Air)
- Best: 131K
- GPT-5 (ChatGPT)
- 128K
Reasoning
- INTELLECT-3 (Based on GLM-4.5-Air)
- Yes
- GPT-5 (ChatGPT)
- No
Open weights
- INTELLECT-3 (Based on GLM-4.5-Air)
- Yes
- GPT-5 (ChatGPT)
- No
Each reasoning level remains a separate configuration.