test-llama2-ko-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1157 ± 40, rank #9859 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.03 | MC2 (%) (0-shot) | 43.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 17.19 | Strict accuracy, prompt/instruction mean (%) | 12.7 |
| Open Korean LLM - KorNAT-CKA | 16.2 | Normalized accuracy (%) | 11.8 |
| Open Korean LLM - KorNAT-Helpful | 41.35 | Normalized accuracy (%) | 11.5 |
| Open LLM Leaderboard v1 - MMLU | 25.62 | Accuracy (%) (5-shot) | 9.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 29.95 | Normalized accuracy (%) (25-shot) | 9 |
| Open Korean LLM Leaderboard | 28.33 | Average Score (%) | 5.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open Korean LLM - Ko-Winogrande | 50.43 | Accuracy (%) | 3.8 |
| Open LLM Leaderboard v1 - HellaSwag | 26.94 | Normalized accuracy (%) (10-shot) | 3.7 |
Interactive version: theaggregate.ai/model?slug=test-llama2-ko-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.