Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Small 3.2
Mistral
- Qwen3 VL 4B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Small 3.2 Mistral | Qwen3 VL 4B (Reasoning) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7 | 7 | |
| Coding | 12.5 | — | |
| Math | Best: 27 | 25.7 | |
| Agentic | 1 | — | |
| Speed | 37 t/s | — | |
| TTFT | 0.92 s | — | |
| Input · $ / 1M tokens | $0.075 | — | |
| Output · $ / 1M tokens | $0.20 | — | |
| Context window | 128K | Best: 256K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.109 | — |
Intelligence
- Mistral Small 3.2
- 7
- Qwen3 VL 4B (Reasoning)
- 7
Coding
- Mistral Small 3.2
- 12.5
- Qwen3 VL 4B (Reasoning)
- —
Math
- Mistral Small 3.2
- Best: 27
- Qwen3 VL 4B (Reasoning)
- 25.7
Agentic
- Mistral Small 3.2
- 1
- Qwen3 VL 4B (Reasoning)
- —
Speed
- Mistral Small 3.2
- 37 t/s
- Qwen3 VL 4B (Reasoning)
- —
TTFT
- Mistral Small 3.2
- 0.92 s
- Qwen3 VL 4B (Reasoning)
- —
Input · $ / 1M tokens
- Mistral Small 3.2
- $0.075
- Qwen3 VL 4B (Reasoning)
- —
Output · $ / 1M tokens
- Mistral Small 3.2
- $0.20
- Qwen3 VL 4B (Reasoning)
- —
Context window
- Mistral Small 3.2
- 128K
- Qwen3 VL 4B (Reasoning)
- Best: 256K
Reasoning
- Mistral Small 3.2
- No
- Qwen3 VL 4B (Reasoning)
- Yes
Open weights
- Mistral Small 3.2
- Yes
- Qwen3 VL 4B (Reasoning)
- Yes
Cost / task
- Mistral Small 3.2
- $0.109
- Qwen3 VL 4B (Reasoning)
- —
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.
- Mistral Small 3.27 · $0.109
Not plotted for lack of data on these axes: Qwen3 VL 4B (Reasoning).