Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Small 4 (Reasoning)
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Small 4 (Reasoning) Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 4.3 | Best: 4.7 | |
| Coding | Best: 26.6 | 17.5 | |
| Agentic | 0.8 | Best: 0.9 | |
| Speed | Best: 166 t/s | 59.2 t/s | |
| TTFT | 0.92 s | Best: 0.91 s | |
| Input · $ / 1M tokens | $0.15×5 relative to the lowest price among the compared models | Best: $0.030 | |
| Output · $ / 1M tokens | $0.60×5 relative to the lowest price among the compared models | Best: $0.12 | |
| Context window | Best: 256K | 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0399×6.6 relative to the lowest price among the compared models | Best: $0.0060 |
Intelligence
- Mistral Small 4 (Reasoning)
- 4.3
- Granite 4.2 3B
- Best: 4.7
Coding
- Mistral Small 4 (Reasoning)
- Best: 26.6
- Granite 4.2 3B
- 17.5
Agentic
- Mistral Small 4 (Reasoning)
- 0.8
- Granite 4.2 3B
- Best: 0.9
Speed
- Mistral Small 4 (Reasoning)
- Best: 166 t/s
- Granite 4.2 3B
- 59.2 t/s
TTFT
- Mistral Small 4 (Reasoning)
- 0.92 s
- Granite 4.2 3B
- Best: 0.91 s
Input · $ / 1M tokens
- Mistral Small 4 (Reasoning)
- $0.15×5 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.030
Output · $ / 1M tokens
- Mistral Small 4 (Reasoning)
- $0.60×5 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.12
Context window
- Mistral Small 4 (Reasoning)
- Best: 256K
- Granite 4.2 3B
- 131K
Reasoning
- Mistral Small 4 (Reasoning)
- Yes
- Granite 4.2 3B
- Yes
Open weights
- Mistral Small 4 (Reasoning)
- Yes
- Granite 4.2 3B
- Yes
Cost / task
- Mistral Small 4 (Reasoning)
- $0.0399×6.6 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.0060
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 4 (Reasoning)4.3 · $0.0399
- Granite 4.2 3B4.7 · $0.0060