| Benchmark | Model | Rank | Results |
|---|---|---|---|
| multi-task-language-understanding-on-include | Apertus-70B-Instruct | #10 | Accuracy: 58.2 |
| common-sense-reasoning-on-winogrande | Apertus-70B | #65 | Accuracy: 73.3 |
| code-generation-on-mbpp | Apertus-70B-Instruct | #120 | Accuracy: 47 |
| math-word-problem-solving-on-math | Apertus-70B-Instruct | #134 | Accuracy: 30.8 |
| sentence-completion-on-hellaswag | Apertus-70B | #136 | Accuracy: 64.0 |
| arithmetic-reasoning-on-gsm8k | Apertus-70B-Instruct | #168 | Accuracy: 77.6 |