ko-Llama-3-8B-sft-v0.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1473 ± 17, rank #1354 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 40.29 | Average Score (%) | 76.2 |
| Open Ko-LLM Leaderboard | 40.29 | Average (%) | 76 |
| Open Korean LLM - Ko-EQ-Bench | 27.55 | EQ-Bench score | 74.7 |
| Open Korean LLM - Ko-IFEval | 34.27 | Strict accuracy, prompt/instruction mean (%) | 70.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 24.72 | Exact match, flexible extract (%) | 58 |
| Open Korean LLM - Ko-Winogrande | 60.14 | Accuracy (%) | 51.6 |
| Open Korean LLM - KorNAT-Helpful | 45.82 | Normalized accuracy (%) | 39.7 |
| Open Korean LLM - KorNAT-CKA | 22.34 | Normalized accuracy (%) | 39.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Harmless | 60.02 | Normalized accuracy (%) | 11.3 |
Interactive version: theaggregate.ai/model?slug=ko-llama-3-8b-sft-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.