AISquare-Instruct-llama2-koen-13B-v0.9.8: benchmark results
Provider: Other. Access: Open.
Unified ELO 1389 ± 17, rank #1984 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.04 | Accuracy (%) | 82.2 |
| Open Korean LLM - KorNAT-CKA | 24.77 | Normalized accuracy (%) | 53.4 |
| Open Korean LLM Leaderboard | 32.93 | Average Score (%) | 36.7 |
| Open Ko-LLM Leaderboard | 32.93 | Average (%) | 36.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 7.43 | Exact match, flexible extract (%) | 29.6 |
| Open Korean LLM - Ko-IFEval | 24.2 | Strict accuracy, prompt/instruction mean (%) | 29.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 43.65 | Normalized accuracy (%) | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.56 | Normalized accuracy (%) | 15.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-8 · How It Works · Data refreshed daily, snapshot 2026-09-19.