AISquare-Instruct-llama2-koen-13B-v0.9.9: benchmark results
Provider: Other. Access: Open.
Unified ELO 1389 ± 17, rank #1982 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.59 | Accuracy (%) | 85.3 |
| Open Korean LLM - KorNAT-CKA | 23.75 | Normalized accuracy (%) | 46.7 |
| Open Korean LLM Leaderboard | 33.01 | Average Score (%) | 37.4 |
| Open Ko-LLM Leaderboard | 33.01 | Average (%) | 37.1 |
| Open Korean LLM - Ko-IFEval | 25.82 | Strict accuracy, prompt/instruction mean (%) | 36.7 |
| Open Korean LLM - KorNAT-Helpful | 44.15 | Normalized accuracy (%) | 27.6 |
| 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 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
| Open Korean LLM - KorNAT-Harmless | 60.37 | Normalized accuracy (%) | 14.1 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-9 · How It Works · Data refreshed daily, snapshot 2026-09-19.