Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1487 ± 58, rank #1201 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 46.24 | Score | 88.7 |
| Open Portuguese LLM - ENEM | 66.76 | Accuracy (%) | 64.6 |
| Open Portuguese LLM - OAB Exams | 46.15 | Accuracy (%) | 63.1 |
| Open LLM Leaderboard - MATH Level 5 | 12.39 | Score | 55.5 |
| Open Portuguese LLM - BLUEX | 53.27 | Accuracy (%) | 55.4 |
| Open LLM Leaderboard - IFEval | 46.73 | Score | 53.3 |
| Open LLM Leaderboard - MMLU-Pro | 33.52 | Score | 47.6 |
| Open LLM Leaderboard - BBH | 49.32 | Score | 45.7 |
| Open Portuguese LLM - ASSIN2 RTE | 88.26 | Macro F1 (%) | 44 |
| Open LLM Leaderboard - GPQA | 28.61 | Score | 41 |
| Open Portuguese LLM - FaQuAD NLI | 39.15 | Macro F1 (%) | 6.9 |
Interactive version: theaggregate.ai/model?slug=fireball-alpaca-llama3-1-08-8b-philos-c-r2 · How It Works · Data refreshed daily, snapshot 2026-09-19.