MiniMA-3B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1259 ± 21, rank #2791 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 45.24 | Macro F1 (%) | 27.6 |
| Open Portuguese LLM - BLUEX | 25.31 | Accuracy (%) | 20.8 |
| Open LLM Leaderboard v1 - GSM8K | 2.73 | Accuracy (%) (5-shot) | 20.7 |
| Open LLM Leaderboard v1 - WinoGrande | 65.98 | Accuracy (%) (5-shot) | 19.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 43.43 | Normalized accuracy (%) (25-shot) | 19.3 |
| Open Portuguese LLM - ASSIN2 RTE | 56.88 | Macro F1 (%) | 19.3 |
| Open LLM Leaderboard v1 - HellaSwag | 68.06 | Normalized accuracy (%) (10-shot) | 19 |
| Open Portuguese LLM - ENEM | 21.2 | Accuracy (%) | 16.9 |
| Open Portuguese LLM - OAB Exams | 25.33 | Accuracy (%) | 16.2 |
| Open LLM Leaderboard v1 - MMLU | 28.69 | Accuracy (%) (5-shot) | 16.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.76 | MC2 (%) (0-shot) | 11.9 |
Interactive version: theaggregate.ai/model?slug=minima-3b · How It Works · Data refreshed daily, snapshot 2026-09-23.