Barcenas-14B-Phi-3-medium-ORPO: benchmark results
Danielbrdz's ORPO fine-tune of SauerkrautLM-Phi-3-medium (Phi-3 14B) on mlabonne's orpo-dpo-mix-40k for conversational use. Provider: Danielbrdz. Released 2024-06-15. Access: Open.
Aggregate Rating 1437 ± 19, rank #1063 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 48.08 | Score | 95 |
| Open LLM Leaderboard - BBH | 65.36 | Score | 92.2 |
| Open Chinese LLM - GSM8K | 65.81 | Accuracy (%) | 90.2 |
| Open Portuguese LLM - BLUEX | 65.79 | Accuracy (%) | 87.3 |
| Open Chinese LLM - ARC Challenge | 59.73 | Accuracy (%) | 86.2 |
| Open Korean LLM - Ko-EQ-Bench | 36.14 | EQ-Bench score | 86.2 |
| Open LLM Leaderboard - MMLU-Pro | 47.23 | Score | 86 |
| Open Portuguese LLM - ENEM | 73.2 | Accuracy (%) | 84.5 |
| Open Chinese LLM Leaderboard | 65.67 | Official Nonzero-Task Mean (%) | 82.5 |
| Open Chinese LLM - WinoGrande | 67.09 | Accuracy (%) | 81.4 |
| Open Portuguese LLM - ASSIN2 RTE | 92.6 | Macro F1 (%) | 80.9 |
| Open Portuguese LLM - OAB Exams | 51.03 | Accuracy (%) | 78.9 |
Interactive version: theaggregate.ai/model?slug=barcenas-14b-phi-3-medium-orpo · How It Works · Data refreshed daily, snapshot 2026-10-20.