ko-Llama-3-8B-Instruct-sft-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1472 ± 17, rank #1359 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 45.19 | Exact match, flexible extract (%) | 80.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-EQ-Bench | 26.16 | EQ-Bench score | 72.9 |
| Open Korean LLM Leaderboard | 39.35 | Average Score (%) | 71.4 |
| Open Ko-LLM Leaderboard | 39.35 | Average (%) | 71.3 |
| Open Korean LLM - KorNAT-Harmless | 63.3 | Normalized accuracy (%) | 59.8 |
| Open Korean LLM - Ko-Winogrande | 60.54 | Accuracy (%) | 55.1 |
| Open Korean LLM - Ko-IFEval | 30.22 | Strict accuracy, prompt/instruction mean (%) | 55 |
| Open Korean LLM - KorNAT-CKA | 25.1 | Normalized accuracy (%) | 54.9 |
| Open Korean LLM - KorNAT-Helpful | 47.15 | Normalized accuracy (%) | 53.5 |
Interactive version: theaggregate.ai/model?slug=ko-llama-3-8b-instruct-sft-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.