Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Magistral Small 1.2
Mistral
- Devstral 2
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Magistral Small 1.2 Mistral | Devstral 2 Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 8.6 | 8.6 | |
| Coding | 14.7 | Best: 31.3 | |
| Math | Best: 80.3 | 36.7 | |
| Agentic | — | 2.3 | |
| Speed | 74.2 t/s | Best: 139 t/s | |
| TTFT | Best: 1.54 s | 2.34 s | |
| Input · $ / 1M tokens | $0.50 | — | |
| Output · $ / 1M tokens | $1.50 | — | |
| Context window | 128K | Best: 256K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes |
Intelligence
- Magistral Small 1.2
- 8.6
- Devstral 2
- 8.6
Coding
- Magistral Small 1.2
- 14.7
- Devstral 2
- Best: 31.3
Math
- Magistral Small 1.2
- Best: 80.3
- Devstral 2
- 36.7
Agentic
- Magistral Small 1.2
- —
- Devstral 2
- 2.3
Speed
- Magistral Small 1.2
- 74.2 t/s
- Devstral 2
- Best: 139 t/s
TTFT
- Magistral Small 1.2
- Best: 1.54 s
- Devstral 2
- 2.34 s
Input · $ / 1M tokens
- Magistral Small 1.2
- $0.50
- Devstral 2
- —
Output · $ / 1M tokens
- Magistral Small 1.2
- $1.50
- Devstral 2
- —
Context window
- Magistral Small 1.2
- 128K
- Devstral 2
- Best: 256K
Reasoning
- Magistral Small 1.2
- Yes
- Devstral 2
- No
Open weights
- Magistral Small 1.2
- Yes
- Devstral 2
- Yes
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.
- Magistral Small 1.28.6 · 74.2 t/s
- Devstral 28.6 · 139 t/s