Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B: benchmark results
Provider: Other. Released 2024-08-07. Access: Open.
Unified ELO 1591 ± 17, rank #665 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 74.07 | Exact match, flexible extract (%) | 98.8 |
| Open Ko-LLM Leaderboard | 51.37 | Average (%) | 97.8 |
| Open Korean LLM Leaderboard | 51.37 | Average Score (%) | 97.8 |
| Open Korean LLM - Ko-EQ-Bench | 50.25 | EQ-Bench score | 95.2 |
| Open Korean LLM - KorNAT-CKA | 34.59 | Normalized accuracy (%) | 94 |
| Open Korean LLM - Ko-IFEval | 49.84 | Strict accuracy, prompt/instruction mean (%) | 93.3 |
| Open Korean LLM - Ko-Winogrande | 68.27 | Accuracy (%) | 92.8 |
| Open Korean LLM - KorNAT-Harmless | 65.66 | Normalized accuracy (%) | 81.7 |
| Open Korean LLM - KorNAT-Helpful | 49.12 | Normalized accuracy (%) | 76.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
Interactive version: theaggregate.ai/model?slug=linkbricks-horizon-ai-korean-gemma-2-sft-dpo-27b · How It Works · Data refreshed daily, snapshot 2026-09-19.