ko-llm-llama-2-7B-chat3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1287 ± 17, rank #2492 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 22.07 | Strict accuracy, prompt/instruction mean (%) | 22.4 |
| Open Korean LLM - KorNAT-CKA | 15.68 | Normalized accuracy (%) | 10.4 |
| Open Ko-LLM Leaderboard | 28.13 | Average (%) | 4.9 |
| Open Korean LLM Leaderboard | 28.13 | Average Score (%) | 4.9 |
| Open Korean LLM - Ko-Winogrande | 50.28 | Accuracy (%) | 3.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
| Open Korean LLM - KorNAT-Helpful | 35.1 | Normalized accuracy (%) | 1 |
| Open Korean LLM - KorNAT-Harmless | 53.25 | Normalized accuracy (%) | 0.4 |
Interactive version: theaggregate.ai/model?slug=ko-llm-llama-2-7b-chat3 · How It Works · Data refreshed daily, snapshot 2026-09-19.