Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 VL 32B (Reasoning)
Alibaba
- Magistral Medium 1.2
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 VL 32B (Reasoning) Alibaba | Magistral Medium 1.2 Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 11.9 | 11.8 | |
| Coding | — | 21.3 | |
| Math | Best: 84.7 | 82 | |
| Speed | 90.7 t/s | — | |
| TTFT | 2.65 s | — | |
| Input · $ / 1M tokens | $0.16 | — | |
| Output · $ / 1M tokens | $0.64 | — | |
| Context window | Best: 256K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No |
Intelligence
- Qwen3 VL 32B (Reasoning)
- Best: 11.9
- Magistral Medium 1.2
- 11.8
Coding
- Qwen3 VL 32B (Reasoning)
- —
- Magistral Medium 1.2
- 21.3
Math
- Qwen3 VL 32B (Reasoning)
- Best: 84.7
- Magistral Medium 1.2
- 82
Speed
- Qwen3 VL 32B (Reasoning)
- 90.7 t/s
- Magistral Medium 1.2
- —
TTFT
- Qwen3 VL 32B (Reasoning)
- 2.65 s
- Magistral Medium 1.2
- —
Input · $ / 1M tokens
- Qwen3 VL 32B (Reasoning)
- $0.16
- Magistral Medium 1.2
- —
Output · $ / 1M tokens
- Qwen3 VL 32B (Reasoning)
- $0.64
- Magistral Medium 1.2
- —
Context window
- Qwen3 VL 32B (Reasoning)
- Best: 256K
- Magistral Medium 1.2
- 128K
Reasoning
- Qwen3 VL 32B (Reasoning)
- Yes
- Magistral Medium 1.2
- Yes
Open weights
- Qwen3 VL 32B (Reasoning)
- Yes
- Magistral Medium 1.2
- No
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 VL 32B (Reasoning)11.9 · $0.28
Not plotted for lack of data on these axes: Magistral Medium 1.2.