Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Small 4 (Reasoning)
Mistral
- DeepSeek R1 (Jan '25)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Small 4 (Reasoning) Mistral | DeepSeek R1 (Jan '25) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 11.3 | Best: 11.4 | |
| Coding | Best: 26.6 | 24.6 | |
| Math | — | 68 | |
| Agentic | 0.8 | Best: 1.1 | |
| Speed | Best: 169 t/s | 148 t/s | |
| TTFT | Best: 0.82 s | 1.09 s | |
| Input · $ / 1M tokens | Best: $0.15 | $2×13.3 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.60 | $4×6.7 relative to the lowest price among the compared models | |
| Context window | Best: 256K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | Best: $0.015 | $0.262×17.4 relative to the lowest price among the compared models |
Intelligence
- Mistral Small 4 (Reasoning)
- 11.3
- DeepSeek R1 (Jan '25)
- Best: 11.4
Coding
- Mistral Small 4 (Reasoning)
- Best: 26.6
- DeepSeek R1 (Jan '25)
- 24.6
Math
- Mistral Small 4 (Reasoning)
- —
- DeepSeek R1 (Jan '25)
- 68
Agentic
- Mistral Small 4 (Reasoning)
- 0.8
- DeepSeek R1 (Jan '25)
- Best: 1.1
Speed
- Mistral Small 4 (Reasoning)
- Best: 169 t/s
- DeepSeek R1 (Jan '25)
- 148 t/s
TTFT
- Mistral Small 4 (Reasoning)
- Best: 0.82 s
- DeepSeek R1 (Jan '25)
- 1.09 s
Input · $ / 1M tokens
- Mistral Small 4 (Reasoning)
- Best: $0.15
- DeepSeek R1 (Jan '25)
- $2×13.3 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Mistral Small 4 (Reasoning)
- Best: $0.60
- DeepSeek R1 (Jan '25)
- $4×6.7 relative to the lowest price among the compared models
Context window
- Mistral Small 4 (Reasoning)
- Best: 256K
- DeepSeek R1 (Jan '25)
- 128K
Reasoning
- Mistral Small 4 (Reasoning)
- Yes
- DeepSeek R1 (Jan '25)
- Yes
Open weights
- Mistral Small 4 (Reasoning)
- Yes
- DeepSeek R1 (Jan '25)
- Yes
Cost / task
- Mistral Small 4 (Reasoning)
- Best: $0.015
- DeepSeek R1 (Jan '25)
- $0.262×17.4 relative to the lowest price among the compared models
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)11.3 · $0.015
- DeepSeek R1 (Jan '25)11.4 · $0.262