Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Nanbeige4.1-3B
Nanbeige
- DeepSeek R1 Distill Qwen 32B
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Nanbeige4.1-3B Nanbeige | DeepSeek R1 Distill Qwen 32B DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 8.4 | 8.4 | |
| Coding | 9.6 | — | |
| Math | — | 63 | |
| Context window | Best: 256K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Nanbeige4.1-3B
- 8.4
- DeepSeek R1 Distill Qwen 32B
- 8.4
Coding
- Nanbeige4.1-3B
- 9.6
- DeepSeek R1 Distill Qwen 32B
- —
Math
- Nanbeige4.1-3B
- —
- DeepSeek R1 Distill Qwen 32B
- 63
Context window
- Nanbeige4.1-3B
- Best: 256K
- DeepSeek R1 Distill Qwen 32B
- 128K
Reasoning
- Nanbeige4.1-3B
- Yes
- DeepSeek R1 Distill Qwen 32B
- Yes
Open weights
- Nanbeige4.1-3B
- Yes
- DeepSeek R1 Distill Qwen 32B
- Yes
Each reasoning level remains a separate configuration.