Satyr-7B-Model_Stock: benchmark results
model_stock merge of NeverSleep/Noromaid-7B-0.4-DPO, SanjiWatsuki/Kunoichi-DPO-v2-7B, Undi95/Toppy-M-7B, Epiculous/Fett-uccine-7B. Base: SanjiWatsuki/Kunoichi-DPO-v2-7B. Exact checkpoint recipe distinguishes the publisher from all parent authors. Provider: DreadPoor. Access: Open.
Aggregate Rating 1443 ± 35, rank #4068 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 86.96 | Normalized accuracy (%) (10-shot) | 83.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 63.76 | MC2 (%) (0-shot) | 81 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.6 | Normalized accuracy (%) (25-shot) | 80.8 |
| Open LLM Leaderboard v1 - MMLU | 65.02 | Accuracy (%) (5-shot) | 80.5 |
| Open LLM Leaderboard v1 - GSM8K | 65.66 | Accuracy (%) (5-shot) | 80.4 |
| Open LLM Leaderboard v1 - WinoGrande | 80.43 | Accuracy (%) (5-shot) | 73.8 |
Interactive version: theaggregate.ai/model?slug=satyr-7b-model-stock · How It Works · Data refreshed daily, snapshot 2026-11-08.