ko-llama2-finetune-ex5: benchmark results
Provider: Other. Access: Open.
Unified ELO 1275 ± 19, rank #2529 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 61.58 | Normalized accuracy (%) | 31.3 |
| Open Korean LLM - Ko-Winogrande | 57.3 | Accuracy (%) | 30.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.46 | Exact match, flexible extract (%) | 24.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 42.35 | Normalized accuracy (%) | 15.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - KorNAT-CKA | 12.35 | Normalized accuracy (%) | 3.1 |
| Open Korean LLM Leaderboard | 27.44 | Average Score (%) | 2.2 |
| Open Ko-LLM Leaderboard | 27.44 | Average (%) | 2.1 |
| Open Korean LLM - Ko-IFEval | 0 | Strict accuracy, prompt/instruction mean (%) | 0.3 |
Interactive version: theaggregate.ai/model?slug=ko-llama2-finetune-ex5 · How It Works · Data refreshed daily, snapshot 2026-09-19.