Model
Phi-3-mini-4k-instruct
Microsoft · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ANLI | 52.8 | score | N/A | Self-reported | medium | arxiv.org |
| BBH | 71.7 | average | N/A | Self-reported | medium | arxiv.org |
| HellaSwag | 76.7 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| LiveBench | 22.4 | global_average | N/A | Independent | medium | livebench.ai |
| MMLU | 68.8 | exact_match | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 88.0 | accuracy | N/A | Self-reported | medium | arxiv.org |
| Trivia QA | 64.0 | exact_match | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 70.8 | accuracy | N/A | Self-reported | medium | arxiv.org |
Reproduced by the community
Loading community runs…