Model
LLaMA 7B
Meta · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARC-Challenge | 47.6 | accuracy | N/A | Independent | medium | arxiv.org |
| ARC-Easy | 72.8 | accuracy | N/A | Independent | medium | arxiv.org |
| BBH | 33.5 | average | N/A | Independent | medium | arxiv.org |
| BBH | 30.3 | average | N/A | Self-reported | medium | arxiv.org |
| BoolQ | 76.5 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 76.5 | score | N/A | Self-reported | medium | arxiv.org |
| BoolQ | 76.5 | score | N/A | Independent | medium | arxiv.org |
| HellaSwag | 76.2 | overall_accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 76.1 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 76.1 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| LAMBADA | 73.3 | score | N/A | Independent | medium | arxiv.org |
| MMLU | 35.6 | exact_match | N/A | Independent | medium | arxiv.org |
| MMLU | 35.1 | exact_match | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 57.2 | accuracy | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 57.2 | accuracy | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 44.2 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 79.8 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 79.8 | score | N/A | Self-reported | medium | arxiv.org |
| PIQA | 79.8 | score | N/A | Independent | medium | arxiv.org |
| ScienceQA | 36.2 | score | N/A | Independent | medium | scienceqa.github.io |
| siqa | 48.9 | accuracy | N/A | Independent | medium | arxiv.org |
| Trivia QA | 71.0 | exact_match | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 70.1 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 70.1 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 69.6 | accuracy | N/A | Independent | medium | arxiv.org |
Math
MathCoding
CodingReproduced by the community
Loading community runs…