Model
GPT-J-6B
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BoolQ | 65.4 | score | N/A | Independent | medium | arxiv.org |
| HellaSwag | 66.2 | overall_accuracy | N/A | Independent | medium | arxiv.org |
| LAMBADA | 69.7 | accuracy | N/A | Independent | medium | paperswithcode.com |
| MMLU | 25.7 | exact_match | N/A | Independent | medium | arxiv.org |
| OpenBookQA | 38.2 | accuracy | N/A | Independent | medium | arxiv.org |
| PIQA | 75.4 | score | N/A | Independent | medium | arxiv.org |
| TruthfulQA | 20.0 | mc1 | N/A | Independent | medium | arxiv.org |
| WinoGrande | 64.5 | accuracy | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…