hkcode-llama3.8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1434 ± 17, rank #1636 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 46.41 | Strict accuracy, prompt/instruction mean (%) | 91.2 |
| Open Korean LLM - KorNAT-CKA | 28.05 | Normalized accuracy (%) | 73.3 |
| Open Korean LLM - Ko-EQ-Bench | 17.9 | EQ-Bench score | 64.3 |
| Open Ko-LLM Leaderboard | 36.13 | Average (%) | 56.2 |
| Open Korean LLM Leaderboard | 36.13 | Average Score (%) | 56.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.29 | Exact match, flexible extract (%) | 54.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Helpful | 42.62 | Normalized accuracy (%) | 17.9 |
| Open Korean LLM - Ko-Winogrande | 54.46 | Accuracy (%) | 16.3 |
| Open Korean LLM - KorNAT-Harmless | 60.22 | Normalized accuracy (%) | 12.5 |
Interactive version: theaggregate.ai/model?slug=hkcode-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.