HighdensityRPMerge-7B: benchmark results
jsfs11 release whose published recipe uses DARE-TIES merging with saishf/West-Hermes-7B as the base and SanjiWatsuki/Silicon-Maid-7B, chargoddard/loyal-piano-m7-cdpo, jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES, NeverSleep/Noromaid-7b-v0.2, athirdpath/NSFW_DPO_vmgb-7b as additional inputs. Provider: jsfs11. Access: Open.
Aggregate Rating 1435 ± 34, rank #4383 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 86.58 | Normalized accuracy (%) (10-shot) | 81.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.41 | Normalized accuracy (%) (25-shot) | 76.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.44 | MC2 (%) (0-shot) | 75.9 |
| Open LLM Leaderboard v1 - MMLU | 64.73 | Accuracy (%) (5-shot) | 75.6 |
| Open LLM Leaderboard v1 - GSM8K | 62.02 | Accuracy (%) (5-shot) | 75 |
| Open LLM Leaderboard v1 - WinoGrande | 79.4 | Accuracy (%) (5-shot) | 69 |
Interactive version: theaggregate.ai/model?slug=highdensityrpmerge-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.