Model
Phi-1.5
Microsoft · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BoolQ | 75.8 | score | N/A | Self-reported | medium | arxiv.org |
| HellaSwag | 47.6 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| MMLU | 37.6 | exact_match | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 37.2 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 73.4 | accuracy | N/A | Self-reported | medium | arxiv.org |
Reproduced by the community
Loading community runs…