mistral-orpo-mix-21k: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1459 ± 20, rank #1652 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 79.48 | Accuracy (%) (5-shot) | 69.4 |
| Open LLM Leaderboard v1 - MMLU | 63.33 | Accuracy (%) (5-shot) | 59.9 |
| Open LLM Leaderboard v1 - HellaSwag | 83.45 | Normalized accuracy (%) (10-shot) | 58.7 |
| Open Portuguese LLM - FaQuAD NLI | 69.14 | Macro F1 (%) | 58.3 |
| Open Portuguese LLM - BLUEX | 53.55 | Accuracy (%) | 56.4 |
| Open LLM Leaderboard v1 - GSM8K | 40.03 | Accuracy (%) (5-shot) | 55.2 |
| Open Portuguese LLM - ASSIN2 RTE | 88.9 | Macro F1 (%) | 47 |
| Open Portuguese LLM - ENEM | 59.2 | Accuracy (%) | 45 |
| Open Portuguese LLM - OAB Exams | 40.73 | Accuracy (%) | 45 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.39 | Normalized accuracy (%) (25-shot) | 43.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.18 | MC2 (%) (0-shot) | 30 |
Interactive version: theaggregate.ai/model?slug=mistral-orpo-mix-21k · How It Works · Data refreshed daily, snapshot 2026-09-23.