Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B: benchmark results
Provider: Other. Released 2024-08-07. Access: Open.
Unified ELO 1575 ± 17, rank #728 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 56.72 | EQ-Bench score | 97.1 |
| Open Ko-LLM Leaderboard | 49.44 | Average (%) | 96.8 |
| Open Korean LLM Leaderboard | 49.44 | Average Score (%) | 96.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 63.53 | Exact match, flexible extract (%) | 96.1 |
| Open Korean LLM - Ko-Winogrande | 69.69 | Accuracy (%) | 95.4 |
| Open Korean LLM - Ko-IFEval | 50.73 | Strict accuracy, prompt/instruction mean (%) | 94 |
| Open Korean LLM - KorNAT-Helpful | 50.88 | Normalized accuracy (%) | 87.8 |
| Open Korean LLM - KorNAT-CKA | 30.16 | Normalized accuracy (%) | 82.3 |
| Open Korean LLM - KorNAT-Harmless | 65.67 | Normalized accuracy (%) | 81.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
Interactive version: theaggregate.ai/model?slug=linkbricks-horizon-ai-korean-mistral-nemo-sft-dpo-12b · How It Works · Data refreshed daily, snapshot 2026-09-19.