Ko-Llama3-Luxia-8B-it: benchmark results
Provider: Other. Access: Open.
Unified ELO 1430 ± 17, rank #1667 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 31.06 | Normalized accuracy (%) | 85.9 |
| Open Korean LLM - Ko-Winogrande | 62.9 | Accuracy (%) | 71.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 30.93 | Exact match, flexible extract (%) | 65.3 |
| Open Ko-LLM Leaderboard | 35.77 | Average (%) | 53.8 |
| Open Korean LLM Leaderboard | 35.77 | Average Score (%) | 53.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 19.67 | Strict accuracy, prompt/instruction mean (%) | 16.8 |
| Open Korean LLM - KorNAT-Helpful | 41.77 | Normalized accuracy (%) | 13.8 |
| Open Korean LLM - KorNAT-Harmless | 60.16 | Normalized accuracy (%) | 12.1 |
Interactive version: theaggregate.ai/model?slug=ko-llama3-luxia-8b-it · How It Works · Data refreshed daily, snapshot 2026-09-19.