Dans-PersonalityEngine-V1.2.0-24B: benchmark results
PocketDoc's multipurpose fine-tune of Mistral Small 24B for roleplay, co-writing, and general instruction tasks. Provider: Other. Released 2025-02-17. Access: Open.
Unified ELO 1586 ± 1, rank #303 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 78.86 | Score | 95.8 |
| Open LLM Leaderboard - MMLU-Pro | 44.73 | Score | 87.9 |
| Open LLM Leaderboard - BBH | 47.56 | Score | 87.5 |
| UGI - Willingness (W/10) | 7.5 | W/10 Score | 77.9 |
| Open LLM Leaderboard - MATH Level 5 | 24.55 | Score | 77.7 |
| Open LLM Leaderboard - GPQA | 9.17 | Score | 74.3 |
| Open LLM Leaderboard - MuSR | 13.38 | Score | 73.7 |
| UGI Leaderboard | 39.54 | UGI Score | 65.2 |
| UGI - Natural Intelligence | 26.03 | NatInt Score | 64.8 |
| UGI - Writing | 30.95 | Writing Score | 40.3 |
Interactive version: theaggregate.ai/model?slug=dans-personalityengine-v1-2-0-24b · How It Works · Data refreshed daily, snapshot 2026-09-05.