Ministrations-8B-v1: benchmark results
TheDrummer's roleplay fine-tune of Mistral's Ministral 8B. Provider: BeaverAI. Released 2024-11-07. Access: Open.
Aggregate Rating 1466 ± 38, rank #2990 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 44.49 | Score | 80.8 |
| Open LLM Leaderboard - GPQA | 32.47 | Score | 78 |
| Open LLM Leaderboard - MATH Level 5 | 18.43 | Score | 68.2 |
| Open LLM Leaderboard - MMLU-Pro | 36.44 | Score | 56.6 |
| Open LLM Leaderboard - BBH | 48.77 | Score | 43.5 |
| UGI - Willingness (W/10) | 5.2 | W/10 Score | 43.1 |
| UGI - Writing | 31.46 | Writing Score | 41.5 |
| Stick To Your Role! - Rank-Order Stability | 0.35 | Rank-Order Stability (correlation, -1 to 1) | 30 |
| StickToYourRole | 49.19 | Cardinal Score | 29 |
| Stick To Your Role! | 0.49 | Cardinal Score (-1 to 1) | 28.3 |
| Open LLM Leaderboard - IFEval | 28.22 | Score | 25.4 |
| UGI Leaderboard | 24.05 | UGI Score | 17.3 |
Interactive version: theaggregate.ai/model?slug=ministrations-8b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.