Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | 8.1 | Best: 8.2 | |
| Math | Best: 63.7 | 41.3 | |
| Context window | 32.8K | Best: 40K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- DeepSeek R1 0528 Qwen3 8B
- 8.1
- Magistral Small 1
- Best: 8.2
Math
- DeepSeek R1 0528 Qwen3 8B
- Best: 63.7
- Magistral Small 1
- 41.3
Context window
- DeepSeek R1 0528 Qwen3 8B
- 32.8K
- Magistral Small 1
- Best: 40K
Reasoning
- DeepSeek R1 0528 Qwen3 8B
- Yes
- Magistral Small 1
- Yes
Open weights
- DeepSeek R1 0528 Qwen3 8B
- Yes
- Magistral Small 1
- Yes
Each reasoning level remains a separate configuration.