Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Magistral Medium 1.2
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Magistral Medium 1.2 Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 11.8 | Best: 11.9 | |
| Coding | 21.3 | — | |
| Math | Best: 82 | 39.3 | |
| Speed | — | 97.4 t/s | |
| TTFT | — | 0.92 s | |
| Input · $ / 1M tokens | — | $0.30 | |
| Output · $ / 1M tokens | — | $1.80 | |
| Context window | 128K | Best: 262K | |
| Reasoning | Yes | No | |
| Open weights | No | Yes |
Intelligence
- Magistral Medium 1.2
- 11.8
- Qwen3 Coder 480B A35B Instruct
- Best: 11.9
Coding
- Magistral Medium 1.2
- 21.3
- Qwen3 Coder 480B A35B Instruct
- —
Math
- Magistral Medium 1.2
- Best: 82
- Qwen3 Coder 480B A35B Instruct
- 39.3
Speed
- Magistral Medium 1.2
- —
- Qwen3 Coder 480B A35B Instruct
- 97.4 t/s
TTFT
- Magistral Medium 1.2
- —
- Qwen3 Coder 480B A35B Instruct
- 0.92 s
Input · $ / 1M tokens
- Magistral Medium 1.2
- —
- Qwen3 Coder 480B A35B Instruct
- $0.30
Output · $ / 1M tokens
- Magistral Medium 1.2
- —
- Qwen3 Coder 480B A35B Instruct
- $1.80
Context window
- Magistral Medium 1.2
- 128K
- Qwen3 Coder 480B A35B Instruct
- Best: 262K
Reasoning
- Magistral Medium 1.2
- Yes
- Qwen3 Coder 480B A35B Instruct
- No
Open weights
- Magistral Medium 1.2
- No
- Qwen3 Coder 480B A35B Instruct
- 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.
- Qwen3 Coder 480B A35B Instruct11.9 · $0.675
Not plotted for lack of data on these axes: Magistral Medium 1.2.