SKY-Ko-Llama3-8B-lora: benchmark results
Provider: Other. Access: Open.
Unified ELO 1485 ± 17, rank #1224 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-EQ-Bench | 31.49 | EQ-Bench score | 80.6 |
| Open Korean LLM Leaderboard | 40.68 | Average Score (%) | 78.6 |
| Open Ko-LLM Leaderboard | 40.68 | Average (%) | 78.5 |
| Open Korean LLM - Ko-IFEval | 36.72 | Strict accuracy, prompt/instruction mean (%) | 76.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 36.16 | Exact match, flexible extract (%) | 69.6 |
| Open Korean LLM - KorNAT-Helpful | 47.33 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-CKA | 23.02 | Normalized accuracy (%) | 42.1 |
| Open Korean LLM - Ko-Winogrande | 58.17 | Accuracy (%) | 36.9 |
| Open Korean LLM - KorNAT-Harmless | 61.48 | Normalized accuracy (%) | 29.5 |
Interactive version: theaggregate.ai/model?slug=sky-ko-llama3-8b-lora · How It Works · Data refreshed daily, snapshot 2026-09-19.