Model
LLaMA 65B
Meta · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARC-Challenge | 56.0 | accuracy | N/A | Independent | medium | arxiv.org |
| ARC-Easy | 78.9 | accuracy | N/A | Independent | medium | arxiv.org |
| BBH | 58.4 | average | N/A | Independent | medium | arxiv.org |
| BBH | 43.5 | average | N/A | Self-reported | medium | arxiv.org |
| BoolQ | 87.1 | score | N/A | Independent | medium | crfm.stanford.edu |
| BoolQ | 85.3 | accuracy | N/A | Independent | medium | arxiv.org |
| BoolQ | 85.3 | score | N/A | Self-reported | medium | arxiv.org |
| HellaSwag | 84.2 | accuracy | N/A | Independent | medium | arxiv.org |
| HellaSwag | 84.2 | overall_accuracy | N/A | Self-reported | medium | arxiv.org |
| LAMBADA | 77.7 | score | N/A | Independent | medium | arxiv.org |
| MMLU | 63.4 | average_(%) | N/A | Independent | medium | arxiv.org |
| MMLU | 63.4 | exact_match | N/A | Self-reported | medium | arxiv.org |
| Natural Questions | 39.9 | exact_match | N/A | Independent | medium | arxiv.org |
| Natural Questions | 35.0 | exact_match | N/A | Independent | medium | arxiv.org |
| Natural Questions | 31.0 | exact_match | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 60.2 | accuracy | N/A | Self-reported | medium | arxiv.org |
| OpenBookQA | 60.2 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 82.8 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 82.8 | score | N/A | Self-reported | medium | arxiv.org |
| PIQA | 82.8 | score | N/A | Independent | medium | arxiv.org |
| siqa | 52.3 | accuracy | N/A | Independent | medium | arxiv.org |
| Trivia QA | 86.0 | exact_match | N/A | Self-reported | medium | arxiv.org |
| Trivia QA | 73.0 | exact_match | N/A | Independent | medium | arxiv.org |
| Trivia QA | 72.6 | exact_match | N/A | Independent | medium | arxiv.org |
| Trivia QA | 71.6 | exact_match | N/A | Independent | medium | arxiv.org |
| Trivia QA | 68.2 | exact_match | N/A | Independent | medium | arxiv.org |
| WinoGrande | 77.0 | accuracy | N/A | Independent | medium | arxiv.org |
| WinoGrande | 77.0 | accuracy | N/A | Self-reported | medium | arxiv.org |
Math
MathCoding
CodingReproduced by the community
Loading community runs…