ko-llama2-13B-finetune-ex: benchmark results
Provider: Other. Access: Open.
Unified ELO 1376 ± 17, rank #2080 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 63.97 | Normalized accuracy (%) | 68.9 |
| Open Korean LLM - Ko-IFEval | 28.74 | Strict accuracy, prompt/instruction mean (%) | 49.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.07 | Exact match, flexible extract (%) | 35.6 |
| Open Korean LLM - Ko-Winogrande | 57.7 | Accuracy (%) | 33.8 |
| Open Korean LLM - KorNAT-Helpful | 44.77 | Normalized accuracy (%) | 32.5 |
| Open Korean LLM Leaderboard | 31.99 | Average Score (%) | 30.4 |
| Open Ko-LLM Leaderboard | 31.99 | Average (%) | 30.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 15.55 | Normalized accuracy (%) | 9.5 |
Interactive version: theaggregate.ai/model?slug=ko-llama2-13b-finetune-ex · How It Works · Data refreshed daily, snapshot 2026-09-19.