yi-ko-playtus-instruct-v0.2: benchmark results
Provider: 01.AI. Access: Open.
Unified ELO 1395 ± 17, rank #1949 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 32.92 | Normalized accuracy (%) | 90 |
| Open Korean LLM - Ko-EQ-Bench | 10.31 | EQ-Bench score | 56.6 |
| Open Korean LLM - KorNAT-Harmless | 62.3 | Normalized accuracy (%) | 41.4 |
| Open Korean LLM Leaderboard | 33.24 | Average Score (%) | 40 |
| Open Ko-LLM Leaderboard | 33.24 | Average (%) | 39.7 |
| Open Korean LLM - Ko-Winogrande | 57.7 | Accuracy (%) | 33.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.97 | Exact match, flexible extract (%) | 29.1 |
| Open Korean LLM - Ko-IFEval | 23.37 | Strict accuracy, prompt/instruction mean (%) | 26.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - KorNAT-Helpful | 41.3 | Normalized accuracy (%) | 11.2 |
Interactive version: theaggregate.ai/model?slug=yi-ko-playtus-instruct-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.