weak-KoRAE-13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1402 ± 18, rank #1894 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 | 29.51 | Normalized accuracy (%) | 80 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-Helpful | 46.58 | Normalized accuracy (%) | 47.5 |
| Open Korean LLM Leaderboard | 33.6 | Average Score (%) | 43 |
| Open Ko-LLM Leaderboard | 33.6 | Average (%) | 42.8 |
| Open Korean LLM - Ko-IFEval | 24.97 | Strict accuracy, prompt/instruction mean (%) | 31.9 |
| Open Korean LLM - KorNAT-Harmless | 60.97 | Normalized accuracy (%) | 21.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.27 | Exact match, flexible extract (%) | 18.5 |
| Open Korean LLM - Ko-EQ-Bench | -2.12 | EQ-Bench score | 3.3 |
Interactive version: theaggregate.ai/model?slug=weak-korae-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.