Cerebrum-1.0-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1456 ± 19, rank #1672 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 77.1 | Macro F1 (%) | 78.6 |
| Open LLM Leaderboard v1 - WinoGrande | 79.4 | Accuracy (%) (5-shot) | 69 |
| Open LLM Leaderboard v1 - HellaSwag | 84.56 | Normalized accuracy (%) (10-shot) | 66.9 |
| Open LLM Leaderboard v1 - MMLU | 63.56 | Accuracy (%) (5-shot) | 61.5 |
| Open Portuguese LLM - OAB Exams | 44.51 | Accuracy (%) | 58.5 |
| Open LLM Leaderboard v1 - GSM8K | 40.18 | Accuracy (%) (5-shot) | 55.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.6 | Normalized accuracy (%) (25-shot) | 53.6 |
| Open Portuguese LLM - ENEM | 61.37 | Accuracy (%) | 49.3 |
| Open Portuguese LLM - BLUEX | 50.63 | Accuracy (%) | 47.8 |
| Open Portuguese LLM - ASSIN2 RTE | 85.63 | Macro F1 (%) | 36.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.49 | MC2 (%) (0-shot) | 34.6 |
| YALL Nous Leaderboard | 48.2 | Average | 29.1 |
Interactive version: theaggregate.ai/model?slug=cerebrum-1-0-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.