llama-p: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1301 ± 18, rank #2457 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 21.89 | Normalized accuracy (%) | 37.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.76 | Exact match, flexible extract (%) | 25.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - Ko-Winogrande | 55.88 | Accuracy (%) | 22.9 |
| Open Korean LLM - KorNAT-Helpful | 41.95 | Normalized accuracy (%) | 14.4 |
| Open Korean LLM - KorNAT-Harmless | 59.99 | Normalized accuracy (%) | 11.1 |
| Open Korean LLM Leaderboard | 28.1 | Average Score (%) | 4.6 |
| Open Ko-LLM Leaderboard | 28.1 | Average (%) | 4.5 |
| Open Korean LLM - Ko-IFEval | 0.97 | Strict accuracy, prompt/instruction mean (%) | 3 |
Interactive version: theaggregate.ai/model?slug=llama-p · How It Works · Data refreshed daily, snapshot 2026-09-19.