Yi-Ko-6B-dpo-v5: benchmark results
Provider: 01.AI. Access: Open.
Unified ELO 1399 ± 17, rank #1913 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 70.06 | Normalized accuracy (%) | 93.3 |
| Open Korean LLM - Ko-Winogrande | 61.4 | Accuracy (%) | 61.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM Leaderboard | 33.35 | Average Score (%) | 41.3 |
| Open Ko-LLM Leaderboard | 33.35 | Average (%) | 41 |
| Open Korean LLM - KorNAT-CKA | 22.59 | Normalized accuracy (%) | 40.3 |
| Open Korean LLM - Ko-IFEval | 24.16 | Strict accuracy, prompt/instruction mean (%) | 29.1 |
| Open Korean LLM - KorNAT-Helpful | 43.95 | Normalized accuracy (%) | 26.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.99 | Exact match, flexible extract (%) | 25.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
Interactive version: theaggregate.ai/model?slug=yi-ko-6b-dpo-v5 · How It Works · Data refreshed daily, snapshot 2026-09-19.