Dans-PersonalityEngine-V1.1.0-12B: benchmark results
PocketDoc's multi-purpose fine-tune of Mistral Nemo Base 12B on 56 datasets spanning roleplay, co-writing, instructions, and tool use. Provider: PocketDoc. Released 2024-12-19. Access: Open.
Aggregate Rating 1497 ± 45, rank #2405 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 45.87 | Score | 87.2 |
| Open LLM Leaderboard - IFEval | 70.75 | Score | 83.9 |
| Open LLM Leaderboard - BBH | 53.61 | Score | 66.8 |
| UGI - Willingness (W/10) | 5.8 | W/10 Score | 50.8 |
| Open LLM Leaderboard - MATH Level 5 | 10.5 | Score | 48.9 |
| Open LLM Leaderboard - MMLU-Pro | 32.62 | Score | 45 |
| Open LLM Leaderboard - GPQA | 28.69 | Score | 41.8 |
| UGI Leaderboard | 32.44 | UGI Score | 40 |
| UGI - Natural Intelligence | 19.48 | NatInt Score | 37.7 |
| UGI - Writing | 27.48 | Writing Score | 28.3 |
Interactive version: theaggregate.ai/model?slug=dans-personalityengine-v1-1-0-12b · How It Works · Data refreshed daily, snapshot 2026-11-08.