Llama 3 10B Ko 240604 E2f: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1476 ± 17, rank #1330 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 29.44 | Normalized accuracy (%) | 79.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 41.85 | Exact match, flexible extract (%) | 76.8 |
| Open Korean LLM Leaderboard | 40.02 | Average Score (%) | 75 |
| Open Ko-LLM Leaderboard | 40.02 | Average (%) | 74.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-EQ-Bench | 21.52 | EQ-Bench score | 66.9 |
| Open Korean LLM - Ko-Winogrande | 60.85 | Accuracy (%) | 58 |
| Open Korean LLM - Ko-IFEval | 28.68 | Strict accuracy, prompt/instruction mean (%) | 49.1 |
| Open Korean LLM - KorNAT-Helpful | 43.5 | Normalized accuracy (%) | 23.8 |
| Open Korean LLM - KorNAT-Harmless | 61.09 | Normalized accuracy (%) | 22.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-10b-ko-240604-e2f · How It Works · Data refreshed daily, snapshot 2026-09-19.