electric-mist-7B: benchmark results
maldv Electric Mist 7B is a story-writing fine-tune of alpindale/Mistral-7B-v0.2-hf using mostly science-fiction text and additional newline-delimited data. The publisher describes 8192-token training samples and explicitly distinguishes the companion LoRA release. Provider: maldv. Access: Open.
Aggregate Rating 1374 ± 34, rank #7048 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.56 | Normalized accuracy (%) (10-shot) | 52.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.18 | Normalized accuracy (%) (25-shot) | 51.6 |
| Open LLM Leaderboard v1 - MMLU | 59.71 | Accuracy (%) (5-shot) | 45.7 |
| Open LLM Leaderboard v1 - GSM8K | 23.5 | Accuracy (%) (5-shot) | 43 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.37 | MC2 (%) (0-shot) | 30.6 |
| Open LLM Leaderboard v1 - WinoGrande | 71.51 | Accuracy (%) (5-shot) | 26.7 |
Interactive version: theaggregate.ai/model?slug=electric-mist-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.