Modelle vergleichen
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | Apertus 70B Instruct | Apertus 8B Instruct |
|---|---|---|
| Artificial Analysis Intelligence Index | 2,4 | 1 |
| GPQA | 27,2% | 25,6% |
| Humanity's Last Exam | 5,5% | 5% |
| SciCode | 5,7% | 4,1% |
| Blended Price | 1,35 $ / 1M | 0,125 $ / 1M |
| Input Price | 0,82 $ / 1M | 0,10 $ / 1M |
| Output Price | 2,92 $ / 1M | 0,20 $ / 1M |
| Value Index | 1,78 | 8 |
