Noromaid-13B-v0.2: benchmark results
An experimental Noromaid role-play release by NeverSleep, credited to Undi and IkariDev. The card describes use of Mergemonster and new datasets; it remains distinct from earlier Noromaid 13B releases. Provider: NeverSleep. Access: Open.
Aggregate Rating 1372 ± 34, rank #7131 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 84.04 | Normalized accuracy (%) (10-shot) | 63.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.58 | MC2 (%) (0-shot) | 56.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.92 | Normalized accuracy (%) (25-shot) | 50.3 |
| Open LLM Leaderboard v1 - GSM8K | 21.76 | Accuracy (%) (5-shot) | 42.1 |
| Open LLM Leaderboard v1 - MMLU | 57.67 | Accuracy (%) (5-shot) | 41.6 |
| Open LLM Leaderboard v1 - WinoGrande | 74.11 | Accuracy (%) (5-shot) | 35 |
Interactive version: theaggregate.ai/model?slug=noromaid-13b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.