Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Small 3
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Small 3 Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 6.7 | 6.7 | |
| Math | 4.3 | — | |
| Speed | 47 t/s | — | |
| TTFT | 0.9 s | — | |
| Input · $ / 1M tokens | Best: $0.050 | $0.66×13.2 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.080 | $1×12.5 relative to the lowest price among the compared models | |
| Context window | Best: 1M | 32.8K | |
| Reasoning | No | — | |
| Open weights | Yes | Yes |
Intelligence
- Mistral Small 3
- 6.7
- Qwen2.5 Coder 32B Instruct
- 6.7
Math
- Mistral Small 3
- 4.3
- Qwen2.5 Coder 32B Instruct
- —
Speed
- Mistral Small 3
- 47 t/s
- Qwen2.5 Coder 32B Instruct
- —
TTFT
- Mistral Small 3
- 0.9 s
- Qwen2.5 Coder 32B Instruct
- —
Input · $ / 1M tokens
- Mistral Small 3
- Best: $0.050
- Qwen2.5 Coder 32B Instruct
- $0.66×13.2 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Mistral Small 3
- Best: $0.080
- Qwen2.5 Coder 32B Instruct
- $1×12.5 relative to the lowest price among the compared models
Context window
- Mistral Small 3
- Best: 1M
- Qwen2.5 Coder 32B Instruct
- 32.8K
Reasoning
- Mistral Small 3
- No
- Qwen2.5 Coder 32B Instruct
- —
Open weights
- Mistral Small 3
- Yes
- Qwen2.5 Coder 32B 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.
- Mistral Small 36.7 · $0.058
- Qwen2.5 Coder 32B Instruct6.7 · $0.745