Llama-2-ko-7B-Chat: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1190 ± 20, rank #9670 of 10916 rated models, from 71 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 29.82 | Accuracy (%) | 62.1 |
| MMLU-by-task - Global Facts | 33 | Accuracy (%) | 51.6 |
| Open Korean LLM - Ko-IFEval | 29.36 | Strict accuracy, prompt/instruction mean (%) | 51.5 |
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - High School Mathematics | 26.3 | Accuracy (%) | 40 |
| MMLU-by-task - Professional Medicine | 43.38 | Accuracy (%) | 38.7 |
| MMLU-by-task - Virology | 34.94 | Accuracy (%) | 37.7 |
| MMLU-by-task - Anatomy | 37.04 | Accuracy (%) | 37.1 |
| MMLU-by-task - Management | 38.83 | Accuracy (%) | 37 |
| MMLU-by-task - Nutrition | 36.93 | Accuracy (%) | 36.7 |
| MMLU-by-task - Jurisprudence | 37.96 | Accuracy (%) | 36.4 |
| MMLU-by-task - Conceptual Physics | 33.62 | Accuracy (%) | 35.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-ko-7b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.