Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral 7B Instruct
Mistral
- Command-R (Mar '24)
Cohere
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral 7B Instruct Mistral | Command-R (Mar '24) Cohere | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5 | 5 | |
| Speed | 84.5 t/s | — | |
| TTFT | 0.79 s | — | |
| Input · $ / 1M tokens | $0.15 | — | |
| Output · $ / 1M tokens | $0.20 | — | |
| Context window | 8K | Best: 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Mistral 7B Instruct
- 5
- Command-R (Mar '24)
- 5
Speed
- Mistral 7B Instruct
- 84.5 t/s
- Command-R (Mar '24)
- —
TTFT
- Mistral 7B Instruct
- 0.79 s
- Command-R (Mar '24)
- —
Input · $ / 1M tokens
- Mistral 7B Instruct
- $0.15
- Command-R (Mar '24)
- —
Output · $ / 1M tokens
- Mistral 7B Instruct
- $0.20
- Command-R (Mar '24)
- —
Context window
- Mistral 7B Instruct
- 8K
- Command-R (Mar '24)
- Best: 128K
Reasoning
- Mistral 7B Instruct
- No
- Command-R (Mar '24)
- No
Open weights
- Mistral 7B Instruct
- Yes
- Command-R (Mar '24)
- 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: Command-R (Mar '24).