Mistral-portuguese-luana-7B: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1452 ± 20, rank #1711 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.35 | MC2 (%) (0-shot) | 73.7 |
| Open Portuguese LLM - ASSIN2 RTE | 90.63 | Macro F1 (%) | 59.2 |
| Open LLM Leaderboard v1 - WinoGrande | 77.74 | Accuracy (%) (5-shot) | 58.2 |
| Open LLM Leaderboard v1 - GSM8K | 38.82 | Accuracy (%) (5-shot) | 53.7 |
| Open LLM Leaderboard v1 - HellaSwag | 82.57 | Normalized accuracy (%) (10-shot) | 52.4 |
| Open LLM Leaderboard v1 - MMLU | 61.15 | Accuracy (%) (5-shot) | 50.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.24 | Normalized accuracy (%) (25-shot) | 46.9 |
| Open Portuguese LLM - ENEM | 58.64 | Accuracy (%) | 44.2 |
| Open Portuguese LLM - FaQuAD NLI | 57.79 | Macro F1 (%) | 41.3 |
| Open Portuguese LLM - BLUEX | 47.98 | Accuracy (%) | 40.7 |
| Open Portuguese LLM - OAB Exams | 38.82 | Accuracy (%) | 39.5 |
Interactive version: theaggregate.ai/model?slug=mistral-portuguese-luana-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.