Dobby-Mini-Unhinged-Llama-3.1-8B: benchmark results
SentientAGI's profane, opinionated 'Unhinged' fine-tune of Llama 3.1 8B Instruct with a fixed pro-freedom, pro-crypto persona. Provider: SentientAGI. Released 2025-01-22. Access: Open.
Unified ELO 1496 ± 1, rank #710 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 74.57 | Score | 89.7 |
| UGI - Willingness (W/10) | 7.5 | W/10 Score | 77.9 |
| Open LLM Leaderboard - GPQA | 7.49 | Score | 63.2 |
| Open LLM Leaderboard - MATH Level 5 | 15.63 | Score | 63.2 |
| Open LLM Leaderboard - MMLU-Pro | 28.72 | Score | 54.3 |
| Open LLM Leaderboard - BBH | 30.37 | Score | 53.1 |
| UGI Leaderboard | 32.13 | UGI Score | 39.2 |
| Open LLM Leaderboard - MuSR | 7.96 | Score | 37.2 |
| UGI - Natural Intelligence | 15.18 | NatInt Score | 19.4 |
| UGI - Writing | 18.75 | Writing Score | 10.6 |
Interactive version: theaggregate.ai/model?slug=dobby-mini-unhinged-llama-3-1-8b · How It Works · Data refreshed daily, snapshot 2026-09-05.