Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mixtral 8x7B Instruct
Mistral
- Apertus 70B Instruct
Swiss AI Initiative
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mixtral 8x7B Instruct Mistral | Apertus 70B Instruct Swiss AI Initiative | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.1 | 5.1 | |
| Speed | 25.5 t/s | — | |
| TTFT | 1.1 s | — | |
| Input · $ / 1M tokens | Best: $0.45 | $0.82×1.8 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.70 | $2.92×4.2 relative to the lowest price among the compared models | |
| Context window | 33K | Best: 66K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Mixtral 8x7B Instruct
- 5.1
- Apertus 70B Instruct
- 5.1
Speed
- Mixtral 8x7B Instruct
- 25.5 t/s
- Apertus 70B Instruct
- —
TTFT
- Mixtral 8x7B Instruct
- 1.1 s
- Apertus 70B Instruct
- —
Input · $ / 1M tokens
- Mixtral 8x7B Instruct
- Best: $0.45
- Apertus 70B Instruct
- $0.82×1.8 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Mixtral 8x7B Instruct
- Best: $0.70
- Apertus 70B Instruct
- $2.92×4.2 relative to the lowest price among the compared models
Context window
- Mixtral 8x7B Instruct
- 33K
- Apertus 70B Instruct
- Best: 66K
Reasoning
- Mixtral 8x7B Instruct
- No
- Apertus 70B Instruct
- No
Open weights
- Mixtral 8x7B Instruct
- Yes
- Apertus 70B 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.
- Mixtral 8x7B Instruct5.1 · $0.512
- Apertus 70B Instruct5.1 · $1.35