AISquare-Instruct-llama2-koen-13B-v0.9.13: benchmark results
Provider: Other. Access: Open.
Unified ELO 1365 ± 17, rank #2142 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.69 | Accuracy (%) | 75.4 |
| Open Korean LLM - KorNAT-Helpful | 47 | Normalized accuracy (%) | 51.7 |
| Open Korean LLM - KorNAT-Harmless | 62.49 | Normalized accuracy (%) | 44.7 |
| Open Korean LLM - KorNAT-CKA | 20.42 | Normalized accuracy (%) | 29.6 |
| Open Korean LLM Leaderboard | 31.43 | Average Score (%) | 27.4 |
| Open Ko-LLM Leaderboard | 31.43 | Average (%) | 27.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.9 | Exact match, flexible extract (%) | 16.5 |
| Open Korean LLM - Ko-IFEval | 17.09 | Strict accuracy, prompt/instruction mean (%) | 12.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
Interactive version: theaggregate.ai/model?slug=aisquare-instruct-llama2-koen-13b-v0-9-13 · How It Works · Data refreshed daily, snapshot 2026-09-19.