mistral-orpo-mix-7k: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1461 ± 20, rank #1629 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 85.51 | Normalized accuracy (%) (10-shot) | 74.9 |
| Open LLM Leaderboard v1 - WinoGrande | 79.72 | Accuracy (%) (5-shot) | 70.7 |
| Open LLM Leaderboard v1 - MMLU | 62.89 | Accuracy (%) (5-shot) | 57.3 |
| Open LLM Leaderboard v1 - GSM8K | 41.24 | Accuracy (%) (5-shot) | 56.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.95 | Normalized accuracy (%) (25-shot) | 55.2 |
| Open Portuguese LLM - OAB Exams | 42.69 | Accuracy (%) | 52.9 |
| Open Portuguese LLM - FaQuAD NLI | 65.88 | Macro F1 (%) | 51.2 |
| Open Portuguese LLM - BLUEX | 51.6 | Accuracy (%) | 50 |
| Open Portuguese LLM - ENEM | 61.51 | Accuracy (%) | 49.6 |
| Open Portuguese LLM - ASSIN2 RTE | 87.95 | Macro F1 (%) | 43 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.91 | MC2 (%) (0-shot) | 35.8 |
Interactive version: theaggregate.ai/model?slug=mistral-orpo-mix-7k · How It Works · Data refreshed daily, snapshot 2026-09-23.