Blured-Ties-7B: benchmark results
liminerity's Blured-Ties-7B is a TIES merge of mistralai/Mistral-7B-v0.1, liminerity/Blurstral-7b-slerp, diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B. The released configuration uses 32 mistral decoder layers; merge recipe dtype is not a measured evaluator precision. Provider: liminerity. Access: Open.
Aggregate Rating 1416 ± 33, rank #5379 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 58.12 | MC2 (%) (0-shot) | 71.7 |
| Open LLM Leaderboard v1 - WinoGrande | 79.72 | Accuracy (%) (5-shot) | 70.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.99 | Normalized accuracy (%) (25-shot) | 65.1 |
| Open LLM Leaderboard v1 - GSM8K | 46.93 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - HellaSwag | 83.56 | Normalized accuracy (%) (10-shot) | 59.7 |
| Open LLM Leaderboard v1 - MMLU | 63.19 | Accuracy (%) (5-shot) | 58.9 |
Interactive version: theaggregate.ai/model?slug=blured-ties-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.