llama3-pre1-ds: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1334 ± 18, rank #2323 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-Helpful | 46.6 | Normalized accuracy (%) | 47.7 |
| Open Korean LLM - KorNAT-Harmless | 62.55 | Normalized accuracy (%) | 45.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 20.44 | Strict accuracy, prompt/instruction mean (%) | 19 |
| Open Korean LLM Leaderboard | 30.03 | Average Score (%) | 16.2 |
| Open Ko-LLM Leaderboard | 30.03 | Average (%) | 16.1 |
| Open Korean LLM - Ko-Winogrande | 51.78 | Accuracy (%) | 7.3 |
| Open Korean LLM - KorNAT-CKA | 14.76 | Normalized accuracy (%) | 7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
Interactive version: theaggregate.ai/model?slug=llama3-pre1-ds · How It Works · Data refreshed daily, snapshot 2026-09-19.