Fireball-Alpaca-Llama-3.1-8B-Philos-DPO-200: benchmark results
Provider: Other. Access: Open.
Unified ELO 1469 ± 56, rank #1385 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 92.52 | Macro F1 (%) | 80 |
| Open Portuguese LLM - OAB Exams | 49.34 | Accuracy (%) | 72.2 |
| Open Portuguese LLM - ENEM | 68.86 | Accuracy (%) | 71.2 |
| Open Portuguese LLM - BLUEX | 56.47 | Accuracy (%) | 66.3 |
| Open Portuguese LLM - FaQuAD NLI | 69.22 | Macro F1 (%) | 58.5 |
| Open LLM Leaderboard - GPQA | 30.03 | Score | 56.5 |
| Open LLM Leaderboard - MATH Level 5 | 12.31 | Score | 55.2 |
| Open LLM Leaderboard - MMLU-Pro | 35.83 | Score | 54.3 |
| Open LLM Leaderboard - IFEval | 45.77 | Score | 51.2 |
| Open LLM Leaderboard - BBH | 48.38 | Score | 42.5 |
| Open LLM Leaderboard - MuSR | 39.45 | Score | 37.9 |
Interactive version: theaggregate.ai/model?slug=fireball-alpaca-llama-3-1-8b-philos-dpo-200 · How It Works · Data refreshed daily, snapshot 2026-09-19.