AISquare-Instruct-llama2-koen-13B-v0.9.14: benchmark results
Provider: Other. Access: Open.
Unified ELO 1409 ± 17, rank #1834 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.17 | Accuracy (%) | 77.4 |
| Open Korean LLM - KorNAT-Helpful | 48.68 | Normalized accuracy (%) | 71.3 |
| Open Korean LLM - KorNAT-Harmless | 63.69 | Normalized accuracy (%) | 65.7 |
| Open Korean LLM Leaderboard | 34.08 | Average Score (%) | 46.2 |
| Open Ko-LLM Leaderboard | 34.08 | Average (%) | 46 |
| Open Korean LLM - Ko-IFEval | 27.52 | Strict accuracy, prompt/instruction mean (%) | 43.5 |
| Open Korean LLM - KorNAT-CKA | 22.55 | Normalized accuracy (%) | 40.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.77 | Exact match, flexible extract (%) | 35.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - Ko-EQ-Bench | -0.46 | EQ-Bench score | 4.8 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-14 · How It Works · Data refreshed daily, snapshot 2026-09-19.