Model
PaLM 2-L
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARC-Challenge | 69.2 | accuracy | N/A | Independent | medium | arxiv.org |
| ARC-Easy | 89.7 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 90.9 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 90.9 | score | N/A | Independent | medium | arxiv.org |
| CommitmentBank | 87.5 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 87.4 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 86.8 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| LAMBADA | 86.9 | accuracy | N/A | Independent | medium | arxiv.org |
| MultiRC | 88.2 | f1 | N/A | Independent | medium | arxiv.org |
| Natural Questions | 37.5 | exact_match | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 58.5 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 85.0 | accuracy | N/A | Independent | medium | arxiv.org |
| RTE | 79.3 | accuracy | N/A | Independent | medium | arxiv.org |
| StoryCloze | 87.4 | accuracy | N/A | Independent | medium | arxiv.org |
| Trivia QA | 86.1 | exact_match | N/A | Independent | medium | arxiv.org |
| Trivia QA | 86.1 | exact_match | N/A | Self-reported | medium | arxiv.org |
| WebQuestions | 28.2 | exact_match | N/A | Independent | medium | arxiv.org |
| WiC | 66.8 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 83.0 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 83.0 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WSC | 86.9 | accuracy | N/A | Independent | medium | arxiv.org |
Multimodal
MultimodalReproduced by the community
Loading community runs…