Lumimaid-v0.2-8B: benchmark results
NeverSleep's roleplay fine-tune of Llama 3.1 8B Instruct on a heavily cleaned RP dataset, the NSFW-capable successor to Lumimaid 0.1. Provider: NeverSleep. Released 2024-07-24. Access: Open.
Aggregate Rating 1455 ± 51, rank #3558 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 43.03 | Score | 70.7 |
| Open LLM Leaderboard - GPQA | 31.12 | Score | 68.5 |
| Open LLM Leaderboard - BBH | 52.38 | Score | 61 |
| Open LLM Leaderboard - MATH Level 5 | 14.35 | Score | 60.7 |
| Open LLM Leaderboard - IFEval | 50.38 | Score | 59.6 |
| Open LLM Leaderboard - MMLU-Pro | 36.36 | Score | 56.3 |
| UGI - Willingness (W/10) | 4.8 | W/10 Score | 38 |
| UGI - Writing | 28.33 | Writing Score | 30.9 |
| UGI Leaderboard | 24.5 | UGI Score | 18.1 |
| UGI - Natural Intelligence | 9.71 | NatInt Score | 6.3 |
Interactive version: theaggregate.ai/model?slug=lumimaid-v0-2-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.