AISquare-Instruct-llama2-koen-13B-v0.9.5: benchmark results
Provider: Other. Access: Open.
Unified ELO 1425 ± 17, rank #1707 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.9 | Accuracy (%) | 86.8 |
| Open Korean LLM - KorNAT-Harmless | 64.19 | Normalized accuracy (%) | 71.5 |
| Open Korean LLM - KorNAT-Helpful | 48.1 | Normalized accuracy (%) | 64.6 |
| Open Korean LLM - KorNAT-CKA | 26.08 | Normalized accuracy (%) | 62.1 |
| Open Korean LLM - Ko-IFEval | 30.91 | Strict accuracy, prompt/instruction mean (%) | 58.5 |
| Open Korean LLM Leaderboard | 35.47 | Average Score (%) | 51.8 |
| Open Ko-LLM Leaderboard | 35.47 | Average (%) | 51.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.95 | Exact match, flexible extract (%) | 42.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-5 · How It Works · Data refreshed daily, snapshot 2026-09-19.