grpo-lora-enem-llama3.7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1478 ± 56, rank #1306 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 92.56 | Macro F1 (%) | 80.2 |
| Open Portuguese LLM - OAB Exams | 49.25 | Accuracy (%) | 71.8 |
| Open Portuguese LLM - ENEM | 68.65 | Accuracy (%) | 70.7 |
| Open Portuguese LLM - BLUEX | 57.3 | Accuracy (%) | 69.4 |
| Open LLM Leaderboard - GPQA | 30.96 | Score | 67.1 |
| Open Portuguese LLM - FaQuAD NLI | 70.03 | Macro F1 (%) | 60.4 |
| Open LLM Leaderboard - MATH Level 5 | 12.16 | Score | 54.6 |
| Open LLM Leaderboard - IFEval | 47.24 | Score | 54.5 |
| Open LLM Leaderboard - MMLU-Pro | 35.74 | Score | 53.9 |
| Open LLM Leaderboard - BBH | 48.01 | Score | 41.5 |
| Open LLM Leaderboard - MuSR | 39.71 | Score | 39.6 |
Interactive version: theaggregate.ai/model?slug=grpo-lora-enem-llama3-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.