Malpyung_Meta-Llama-3.1-8B_SFT: benchmark results
Provider: Other. Access: Open.
Unified ELO 1531 ± 17, rank #933 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 Ko-LLM Leaderboard | 45.11 | Average (%) | 91.3 |
| Open Korean LLM Leaderboard | 45.11 | Average Score (%) | 91.3 |
| Open Korean LLM - Ko-IFEval | 46.11 | Strict accuracy, prompt/instruction mean (%) | 90.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 54.21 | Exact match, flexible extract (%) | 88.2 |
| Open Korean LLM - Ko-EQ-Bench | 31.39 | EQ-Bench score | 80.6 |
| Open Korean LLM - KorNAT-CKA | 29.46 | Normalized accuracy (%) | 79.6 |
| Open Korean LLM - Ko-Winogrande | 60.46 | Accuracy (%) | 54.5 |
| Open Korean LLM - KorNAT-Helpful | 44.25 | Normalized accuracy (%) | 28.1 |
| Open Korean LLM - KorNAT-Harmless | 60.65 | Normalized accuracy (%) | 16.8 |
Interactive version: theaggregate.ai/model?slug=malpyung-meta-llama-3-1-8b-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.