Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Gemma 3 4B Instruct
Google
- Apertus 8B Instruct
Swiss AI Initiative
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Gemma 3 4B Instruct | Apertus 8B Instruct Swiss AI Initiative | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 4.8 | 4.8 | |
| Coding | 2.7 | — | |
| Math | 12.7 | — | |
| Input · $ / 1M tokens | — | $0.10 | |
| Output · $ / 1M tokens | — | $0.20 | |
| Context window | Best: 128K | 66K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Gemma 3 4B Instruct
- 4.8
- Apertus 8B Instruct
- 4.8
Coding
- Gemma 3 4B Instruct
- 2.7
- Apertus 8B Instruct
- —
Math
- Gemma 3 4B Instruct
- 12.7
- Apertus 8B Instruct
- —
Input · $ / 1M tokens
- Gemma 3 4B Instruct
- —
- Apertus 8B Instruct
- $0.10
Output · $ / 1M tokens
- Gemma 3 4B Instruct
- —
- Apertus 8B Instruct
- $0.20
Context window
- Gemma 3 4B Instruct
- Best: 128K
- Apertus 8B Instruct
- 66K
Reasoning
- Gemma 3 4B Instruct
- No
- Apertus 8B Instruct
- No
Open weights
- Gemma 3 4B Instruct
- Yes
- Apertus 8B 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.
- Apertus 8B Instruct4.8 · $0.125
Not plotted for lack of data on these axes: Gemma 3 4B Instruct.