yi-ko-6B-dpo-further: benchmark results
Provider: 01.AI. Access: Open.
Unified ELO 1397 ± 17, rank #1938 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 28.99 | Normalized accuracy (%) | 78.1 |
| Open Korean LLM - Ko-Winogrande | 61.25 | Accuracy (%) | 60.9 |
| Open Korean LLM - Ko-EQ-Bench | 0.93 | EQ-Bench score | 46.4 |
| Open Korean LLM Leaderboard | 33.26 | Average Score (%) | 40.3 |
| Open Ko-LLM Leaderboard | 33.26 | Average (%) | 40 |
| Open Korean LLM - Ko-IFEval | 26.47 | Strict accuracy, prompt/instruction mean (%) | 39 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.83 | Exact match, flexible extract (%) | 37.6 |
| Open Korean LLM - KorNAT-Helpful | 43.8 | Normalized accuracy (%) | 25.5 |
| Open Korean LLM - KorNAT-Harmless | 59.65 | Normalized accuracy (%) | 8 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.69 | Normalized accuracy (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=yi-ko-6b-dpo-further · How It Works · Data refreshed daily, snapshot 2026-09-19.