Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Apertus 70B Instruct
Swiss AI Initiative
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Apertus 70B Instruct Swiss AI Initiative | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 5.1 | 5.1 | |
| Coding | 22.4 | — | |
| Agentic | 1.3 | — | |
| Speed | 58.6 t/s | — | |
| TTFT | 0.73 s | — | |
| Input · $ / 1M tokens | Best: $0.060 | $0.82×13.7 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.25 | $2.92×11.7 relative to the lowest price among the compared models | |
| Context window | Best: 131K | 66K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0405 | — |
Intelligence
- Granite 4.2 8B
- 5.1
- Apertus 70B Instruct
- 5.1
Coding
- Granite 4.2 8B
- 22.4
- Apertus 70B Instruct
- —
Agentic
- Granite 4.2 8B
- 1.3
- Apertus 70B Instruct
- —
Speed
- Granite 4.2 8B
- 58.6 t/s
- Apertus 70B Instruct
- —
TTFT
- Granite 4.2 8B
- 0.73 s
- Apertus 70B Instruct
- —
Input · $ / 1M tokens
- Granite 4.2 8B
- Best: $0.060
- Apertus 70B Instruct
- $0.82×13.7 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Granite 4.2 8B
- Best: $0.25
- Apertus 70B Instruct
- $2.92×11.7 relative to the lowest price among the compared models
Context window
- Granite 4.2 8B
- Best: 131K
- Apertus 70B Instruct
- 66K
Reasoning
- Granite 4.2 8B
- Yes
- Apertus 70B Instruct
- No
Open weights
- Granite 4.2 8B
- Yes
- Apertus 70B Instruct
- Yes
Cost / task
- Granite 4.2 8B
- $0.0405
- Apertus 70B Instruct
- —
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.
- Granite 4.2 8B5.1 · $0.107
- Apertus 70B Instruct5.1 · $1.35