Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Apertus 70B Instruct
Swiss AI Initiative
- IBM: Granite 4.0 Micro
Ibm Granite
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Apertus 70B Instruct Swiss AI Initiative | IBM: Granite 4.0 Micro Ibm Granite | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.1 | 5.1 | |
| Input · $ / 1M tokens | $0.82×48.2 relative to the lowest price among the compared models | Best: $0.017 | |
| Output · $ / 1M tokens | $2.92×26.1 relative to the lowest price among the compared models | Best: $0.112 | |
| Context window | 66K | Best: 131K | |
| Reasoning | No | — | |
| Open weights | Yes | Yes |
Intelligence
- Apertus 70B Instruct
- 5.1
- IBM: Granite 4.0 Micro
- 5.1
Input · $ / 1M tokens
- Apertus 70B Instruct
- $0.82×48.2 relative to the lowest price among the compared models
- IBM: Granite 4.0 Micro
- Best: $0.017
Output · $ / 1M tokens
- Apertus 70B Instruct
- $2.92×26.1 relative to the lowest price among the compared models
- IBM: Granite 4.0 Micro
- Best: $0.112
Context window
- Apertus 70B Instruct
- 66K
- IBM: Granite 4.0 Micro
- Best: 131K
Reasoning
- Apertus 70B Instruct
- No
- IBM: Granite 4.0 Micro
- —
Open weights
- Apertus 70B Instruct
- Yes
- IBM: Granite 4.0 Micro
- 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.
- Apertus 70B Instruct5.1 · $1.35
- IBM: Granite 4.0 Micro5.1 · $0.0408