dolphin-2.9-llama3-8B: benchmark results
Provider: Cognitive Computations. Released 2024-04-20. Access: Open.
Unified ELO 1432 ± 40, rank #1648 of 2656 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 43.75 | Score | 76.4 |
| Open Portuguese LLM - FaQuAD NLI | 72.43 | Macro F1 (%) | 65.7 |
| Open Portuguese LLM - ASSIN2 RTE | 90.06 | Macro F1 (%) | 53.8 |
| Open Portuguese LLM - ENEM | 60.04 | Accuracy (%) | 46.9 |
| Open LLM Leaderboard - BBH | 49.5 | Score | 46.3 |
| Open Portuguese LLM - BLUEX | 49.65 | Accuracy (%) | 45.6 |
| Open LLM Leaderboard - GPQA | 28.69 | Score | 41.8 |
| YALL Nous Leaderboard | 50.8 | Average | 38.6 |
| Open LLM Leaderboard - IFEval | 38.5 | Score | 37.8 |
| Open Portuguese LLM - OAB Exams | 37.86 | Accuracy (%) | 36.2 |
| Open LLM Leaderboard - MATH Level 5 | 5.74 | Score | 31.8 |
| Open LLM Leaderboard - MMLU-Pro | 27.71 | Score | 30.3 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-9-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.