Uncensored-Frank-7B: benchmark results
A conversation fine-tune by ajibawa-2023 trained on approximately 150,000 conversation sets. The card describes a mixture derived from wizard_vicuna_70k_unfiltered and additional synthetic conversations. The final training dataset is not released according to the card. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1235 ± 16, rank #9376 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Global Facts | 34 | Accuracy (%) | 58.4 |
| MMLU-by-task - Conceptual Physics | 41.28 | Accuracy (%) | 58.2 |
| MMLU-by-task - TruthfulQA MC1 | 29.38 | Accuracy (%) | 54.6 |
| MMLU-by-task - Professional Medicine | 47.79 | Accuracy (%) | 53.6 |
| MMLU-by-task - Abstract Algebra | 30 | Accuracy (%) | 52.2 |
| MMLU-by-task - ARC Challenge | 49.91 | Accuracy (%) | 50.5 |
| MMLU-by-task - HellaSwag | 58.21 | Accuracy (%) | 47.5 |
| MMLU-by-task - Medical Genetics | 49 | Accuracy (%) | 46.6 |
| MMLU-by-task - High School Computer Science | 41 | Accuracy (%) | 46.2 |
| MMLU-by-task - TruthfulQA MC2 | 43.86 | Accuracy (%) | 45.8 |
| MMLU-by-task - College Mathematics | 31 | Accuracy (%) | 45.5 |
| MMLU-by-task - High School US History | 50.98 | Accuracy (%) | 44.8 |
Interactive version: theaggregate.ai/model?slug=uncensored-frank-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.