OPI-Llama-3.1-8B-Instruct: benchmark results
Provider: Other. Access: Open.
Unified ELO 1257 ± 59, rank #2566 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - OAB Exams | 36.31 | Accuracy (%) | 34 |
| Open Portuguese LLM - ENEM | 42.83 | Accuracy (%) | 31.1 |
| Open LLM Leaderboard - GPQA | 27.43 | Score | 29.4 |
| Open Portuguese LLM - BLUEX | 32.68 | Accuracy (%) | 28.4 |
| Open LLM Leaderboard - MMLU-Pro | 21.24 | Score | 22.3 |
| Open LLM Leaderboard - BBH | 35.51 | Score | 20 |
| Open LLM Leaderboard - IFEval | 20.75 | Score | 13.1 |
| Open LLM Leaderboard - MATH Level 5 | 1.36 | Score | 9.9 |
| Open Portuguese LLM - ASSIN2 RTE | 33.64 | Macro F1 (%) | 7.9 |
| Open Portuguese LLM - FaQuAD NLI | 17.72 | Macro F1 (%) | 3.5 |
| Open LLM Leaderboard - MuSR | 32.33 | Score | 2.3 |
Interactive version: theaggregate.ai/model?slug=opi-llama-3-1-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.