Qwen-2.5-Base-7B-SFT-Korean-Article-Dataset: benchmark results
Provider: Alibaba. Access: Open.
Unified ELO 1407 ± 18, rank #1848 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.73 | Normalized accuracy (%) | 81.4 |
| Open Korean LLM - KorNAT-CKA | 25.57 | Normalized accuracy (%) | 58.9 |
| Open Korean LLM - Ko-Winogrande | 60.93 | Accuracy (%) | 58.7 |
| Open Korean LLM - Ko-EQ-Bench | 9.9 | EQ-Bench score | 55.8 |
| Open Korean LLM - KorNAT-Harmless | 62.77 | Normalized accuracy (%) | 49.9 |
| Open Korean LLM Leaderboard | 34 | Average Score (%) | 45.7 |
| Open Ko-LLM Leaderboard | 34 | Average (%) | 45.5 |
| Open Korean LLM - Ko-IFEval | 25.15 | Strict accuracy, prompt/instruction mean (%) | 33.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.08 | Exact match, flexible extract (%) | 4.8 |
Interactive version: theaggregate.ai/model?slug=qwen-2-5-base-7b-sft-korean-article-dataset · How It Works · Data refreshed daily, snapshot 2026-09-19.