notux-8x7B-v1: benchmark results
Argilla's Notux 8x7B, a DPO preference-tuned version of Mixtral-8x7B-Instruct-v0.1 trained on their cleaned UltraFeedback preference dataset. Provider: Argilla. Released 2023-12-12. Access: Open.
Aggregate Rating 1458 ± 29, rank #930 of 1635 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 71.39 | Accuracy (%) (5-shot) | 95 |
| Open Portuguese LLM - FaQuAD NLI | 79.85 | Macro F1 (%) | 88.6 |
| Open LLM Leaderboard v1 - HellaSwag | 87.72 | Normalized accuracy (%) (10-shot) | 87.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.65 | Normalized accuracy (%) (25-shot) | 86.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 66.21 | MC2 (%) (0-shot) | 84.6 |
| Open Portuguese LLM - ASSIN2 RTE | 92.66 | Macro F1 (%) | 81.9 |
| Open Portuguese LLM - ENEM | 70.96 | Accuracy (%) | 78.3 |
| Open Portuguese LLM - BLUEX | 60.22 | Accuracy (%) | 78 |
| Open LLM Leaderboard v1 - WinoGrande | 80.74 | Accuracy (%) (5-shot) | 75.4 |
| Open LLM Leaderboard v1 - GSM8K | 61.11 | Accuracy (%) (5-shot) | 73.5 |
| Open Portuguese LLM - OAB Exams | 49.52 | Accuracy (%) | 73.1 |
| Open LLM Leaderboard - BBH | 53.63 | Score | 67 |
Interactive version: theaggregate.ai/model?slug=notux-8x7b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-05.