llama3.1-korean-v1.6-sft-by-aidx: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1548 ± 17, rank #846 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 46.93 | Average Score (%) | 94.2 |
| Open Ko-LLM Leaderboard | 46.93 | Average (%) | 94.1 |
| Open Korean LLM - KorNAT-CKA | 33.57 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 57.62 | Exact match, flexible extract (%) | 92 |
| Open Korean LLM - Ko-IFEval | 45.68 | Strict accuracy, prompt/instruction mean (%) | 90.2 |
| Open Korean LLM - Ko-EQ-Bench | 38.94 | EQ-Bench score | 90 |
| Open Korean LLM - KorNAT-Harmless | 63.62 | Normalized accuracy (%) | 64.9 |
| Open Korean LLM - KorNAT-Helpful | 47.42 | Normalized accuracy (%) | 56.7 |
| Open Korean LLM - Ko-Winogrande | 60.46 | Accuracy (%) | 54.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
Interactive version: theaggregate.ai/model?slug=llama3-1-korean-v1-6-sft-by-aidx · How It Works · Data refreshed daily, snapshot 2026-09-19.