Half-NSFW_Noromaid-7B: benchmark results
Azazelle's SLERP merge, whose published recipe uses mistralai/Mistral-7B-v0.1 as its base and NeverSleep/Noromaid-7b-v0.2, athirdpath/NSFW_DPO_Noromaid-7b as merge inputs. Its published Mistral configuration specifies 32 decoder layers. Provider: Azazelle. Access: Open.
Aggregate Rating 1407 ± 33, rank #5739 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 84.82 | Normalized accuracy (%) (10-shot) | 69 |
| Open LLM Leaderboard v1 - MMLU | 63.76 | Accuracy (%) (5-shot) | 63.1 |
| Open LLM Leaderboard v1 - WinoGrande | 78.06 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.8 | Normalized accuracy (%) (25-shot) | 59.8 |
| Open LLM Leaderboard v1 - GSM8K | 38.44 | Accuracy (%) (5-shot) | 53.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.05 | MC2 (%) (0-shot) | 33.2 |
Interactive version: theaggregate.ai/model?slug=half-nsfw-noromaid-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.