Model
Meta-Llama-3-8B-Instruct
Meta AI
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ANLI | 57.3 | score | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 26.1 | accuracy | N/A | Independent | high | epoch.ai |
| MMLU | 68.8 | exact_match | N/A | Independent | medium | crfm.stanford.edu |
| OpenBookQA | 82.6 | accuracy | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 45.0 | accuracy | N/A | Self-reported | medium | arxiv.org |
| Trivia QA | 67.7 | exact_match | N/A | Independent | medium | arxiv.org |
| WinoGrande | 75.7 | accuracy | N/A | Self-reported | medium | arxiv.org |
| WinoGrande | 65.0 | accuracy | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…