AISquare-Instruct-llama2-koen-13B-v0.9.3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1400 ± 17, rank #1909 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.56 | Accuracy (%) | 79.5 |
| Open Korean LLM - KorNAT-CKA | 25.28 | Normalized accuracy (%) | 56.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.48 | Exact match, flexible extract (%) | 42.9 |
| Open Korean LLM Leaderboard | 33.38 | Average Score (%) | 41.4 |
| Open Ko-LLM Leaderboard | 33.38 | Average (%) | 41.2 |
| Open Korean LLM - KorNAT-Harmless | 61.92 | Normalized accuracy (%) | 35.9 |
| Open Korean LLM - Ko-IFEval | 23.34 | Strict accuracy, prompt/instruction mean (%) | 26.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 42.65 | Normalized accuracy (%) | 18.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-3 · How It Works · Data refreshed daily, snapshot 2026-09-19.