SauerkrautLM-Mixtral-8x7B: benchmark results
A VAGOsolutions fine-tune of mistralai/Mixtral-8x7B-v0.1 using supervised fine-tuning and DPO, with German data augmentation and translated data. It remains distinct from the separate release initialized from Mixtral Instruct. Provider: VAGOsolutions. Access: Open.
Aggregate Rating 1450 ± 34, rank #3783 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.69 | Accuracy (%) (5-shot) | 87.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.86 | Normalized accuracy (%) (25-shot) | 81.6 |
| Open LLM Leaderboard v1 - HellaSwag | 86.01 | Normalized accuracy (%) (10-shot) | 78.1 |
| Open LLM Leaderboard v1 - WinoGrande | 80.51 | Accuracy (%) (5-shot) | 74.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 57.2 | MC2 (%) (0-shot) | 69.6 |
| Open LLM Leaderboard v1 - GSM8K | 47.54 | Accuracy (%) (5-shot) | 60.8 |
| German Public Sector Benchmark | 0.61 | Party-Position Classification Accuracy (0-1) | 11.1 |
Interactive version: theaggregate.ai/model?slug=sauerkrautlm-mixtral-8x7b · How It Works · Data refreshed daily, snapshot 2026-11-08.