West-Dare-7B: benchmark results
jsfs11 release whose published recipe uses TIES merging with mistralai/Mistral-7B-v0.1 as the base and senseable/Westlake-7B, abideen/DareVox-7B as additional inputs. The recipe specifies ties; the name alone does not establish a DARE merge. Provider: jsfs11. Access: Open.
Aggregate Rating 1458 ± 40, rank #3434 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 84.53 | Accuracy (%) (5-shot) | 93.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.42 | Normalized accuracy (%) (25-shot) | 89.2 |
| Open LLM Leaderboard v1 - HellaSwag | 87.57 | Normalized accuracy (%) (10-shot) | 86.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 66.25 | MC2 (%) (0-shot) | 84.6 |
| Open LLM Leaderboard v1 - GSM8K | 67.85 | Accuracy (%) (5-shot) | 84.5 |
| Open LLM Leaderboard v1 - MMLU | 64.29 | Accuracy (%) (5-shot) | 67.7 |
Interactive version: theaggregate.ai/model?slug=west-dare-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.