Wingless_Imp_8B: benchmark results
SicariusSicariiStuff's Llama 3/3.1 8B merge (Impish_Mind, Unaligned_BETA, Dusk_Rainbow) tuned for roleplay and creative writing. Provider: SicariusSicariiStuff. Released 2025-01-24. Access: Open.
Aggregate Rating 1448 ± 47, rank #3854 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 74.3 | Score | 89.3 |
| UGI - Willingness (W/10) | 6.8 | W/10 Score | 67.6 |
| Open LLM Leaderboard - MMLU-Pro | 36.39 | Score | 56.4 |
| Open LLM Leaderboard - MuSR | 41.48 | Score | 55 |
| Open LLM Leaderboard - BBH | 51.2 | Score | 54.9 |
| Open LLM Leaderboard - MATH Level 5 | 12.01 | Score | 53.9 |
| UGI Leaderboard | 33.47 | UGI Score | 44.4 |
| Open LLM Leaderboard - GPQA | 28.27 | Score | 37.6 |
| UGI - Writing | 23.51 | Writing Score | 18.9 |
| UGI - Natural Intelligence | 11 | NatInt Score | 8 |
Interactive version: theaggregate.ai/model?slug=wingless-imp-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.