Model
PaLM 2-M
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARC-Challenge | 64.9 | accuracy | N/A | Independent | medium | arxiv.org |
| ARC-Easy | 88.0 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 88.6 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 88.6 | score | N/A | Independent | medium | arxiv.org |
| CommitmentBank | 80.4 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 86.7 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 84.0 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| LAMBADA | 83.7 | accuracy | N/A | Independent | medium | arxiv.org |
| MultiRC | 84.1 | f1 | N/A | Independent | medium | arxiv.org |
| Natural Questions | 32.0 | exact_match | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 57.4 | accuracy | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 56.2 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 83.2 | accuracy | N/A | Independent | medium | arxiv.org |
| RTE | 81.9 | accuracy | N/A | Independent | medium | arxiv.org |
| StoryCloze | 86.7 | accuracy | N/A | Independent | medium | arxiv.org |
| Trivia QA | 81.7 | exact_match | N/A | Independent | medium | arxiv.org |
| Trivia QA | 81.7 | exact_match | N/A | Self-reported | medium | arxiv.org |
| WebQuestions | 26.9 | exact_match | N/A | Independent | medium | arxiv.org |
| WiC | 52.0 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 79.2 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 79.2 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WSC | 88.1 | accuracy | N/A | Independent | medium | arxiv.org |
Multimodal
MultimodalReproduced by the community
Loading community runs…