Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral 7B Instruct
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral 7B Instruct Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 5 | 5 | |
| Math | 6.3 | — | |
| Speed | — | 84.5 t/s | |
| TTFT | — | 0.79 s | |
| Input · $ / 1M tokens | — | $0.15 | |
| Output · $ / 1M tokens | — | $0.20 | |
| Context window | Best: 128K | 8K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Granite 4.0 1B
- 5
- Mistral 7B Instruct
- 5
Math
- Granite 4.0 1B
- 6.3
- Mistral 7B Instruct
- —
Speed
- Granite 4.0 1B
- —
- Mistral 7B Instruct
- 84.5 t/s
TTFT
- Granite 4.0 1B
- —
- Mistral 7B Instruct
- 0.79 s
Input · $ / 1M tokens
- Granite 4.0 1B
- —
- Mistral 7B Instruct
- $0.15
Output · $ / 1M tokens
- Granite 4.0 1B
- —
- Mistral 7B Instruct
- $0.20
Context window
- Granite 4.0 1B
- Best: 128K
- Mistral 7B Instruct
- 8K
Reasoning
- Granite 4.0 1B
- No
- Mistral 7B Instruct
- No
Open weights
- Granite 4.0 1B
- Yes
- Mistral 7B 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 7B Instruct5 · $0.162
Not plotted for lack of data on these axes: Granite 4.0 1B.