Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1556 ± 17, rank #817 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 53.1 | Strict accuracy, prompt/instruction mean (%) | 95.7 |
| Open Ko-LLM Leaderboard | 47.94 | Average (%) | 95.3 |
| Open Korean LLM Leaderboard | 47.94 | Average Score (%) | 95.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 61.56 | Exact match, flexible extract (%) | 95 |
| Open Korean LLM - Ko-EQ-Bench | 37.17 | EQ-Bench score | 88 |
| Open Korean LLM - KorNAT-CKA | 30.48 | Normalized accuracy (%) | 83.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - KorNAT-Harmless | 63.36 | Normalized accuracy (%) | 61.3 |
| Open Korean LLM - Ko-Winogrande | 61.01 | Accuracy (%) | 59.2 |
| Open Korean LLM - KorNAT-Helpful | 47.33 | Normalized accuracy (%) | 55.6 |
Interactive version: theaggregate.ai/model?slug=linkbricks-horizon-ai-korean-llama-3-1-sft-dpo-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.