Uncensored-Jordan-7B: benchmark results
A conversation fine-tune by ajibawa-2023 on approximately 155,000 conversation sets; the card states that its training data will not be released. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1293 ± 34, rank #8836 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.5 | MC2 (%) (0-shot) | 37.9 |
| Open LLM Leaderboard v1 - HellaSwag | 77.37 | Normalized accuracy (%) (10-shot) | 30.7 |
| Open LLM Leaderboard v1 - GSM8K | 6.75 | Accuracy (%) (5-shot) | 25.9 |
| Open LLM Leaderboard v1 - WinoGrande | 71.11 | Accuracy (%) (5-shot) | 25.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 51.28 | Normalized accuracy (%) (25-shot) | 25.7 |
| Open LLM Leaderboard v1 - MMLU | 45.69 | Accuracy (%) (5-shot) | 24.2 |
Interactive version: theaggregate.ai/model?slug=uncensored-jordan-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.