openchat3.5-korean-v1.0-sft: benchmark results
Provider: Other. Access: Open.
Unified ELO 1476 ± 17, rank #1331 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 38.79 | EQ-Bench score | 89.6 |
| Open Korean LLM Leaderboard | 40.49 | Average Score (%) | 77.4 |
| Open Ko-LLM Leaderboard | 40.49 | Average (%) | 77.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37 | Exact match, flexible extract (%) | 70.6 |
| Open Korean LLM - Ko-IFEval | 33.79 | Strict accuracy, prompt/instruction mean (%) | 68.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-Winogrande | 56.35 | Accuracy (%) | 25.8 |
| Open Korean LLM - KorNAT-CKA | 19.59 | Normalized accuracy (%) | 25.5 |
| Open Korean LLM - KorNAT-Helpful | 42.85 | Normalized accuracy (%) | 19.2 |
| Open Korean LLM - KorNAT-Harmless | 59.54 | Normalized accuracy (%) | 7.1 |
Interactive version: theaggregate.ai/model?slug=openchat3-5-korean-v1-0-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.