llama3.1-korean-v0.1-sft-by-aidx: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1530 ± 17, rank #938 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 46.92 | Strict accuracy, prompt/instruction mean (%) | 91.5 |
| Open Korean LLM Leaderboard | 44.99 | Average Score (%) | 91.3 |
| Open Ko-LLM Leaderboard | 44.99 | Average (%) | 91.2 |
| Open Korean LLM - Ko-EQ-Bench | 39.79 | EQ-Bench score | 91.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 55.04 | Exact match, flexible extract (%) | 88.9 |
| Open Korean LLM - KorNAT-CKA | 30.36 | Normalized accuracy (%) | 82.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-Winogrande | 59.67 | Accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-Harmless | 62.33 | Normalized accuracy (%) | 41.8 |
| Open Korean LLM - KorNAT-Helpful | 43.35 | Normalized accuracy (%) | 23.3 |
Interactive version: theaggregate.ai/model?slug=llama3-1-korean-v0-1-sft-by-aidx · How It Works · Data refreshed daily, snapshot 2026-09-19.