test-llama2.7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1302 ± 17, rank #2452 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-Winogrande | 57.7 | Accuracy (%) | 33.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5 | Exact match, flexible extract (%) | 23.9 |
| Open Korean LLM - KorNAT-Harmless | 60.49 | Normalized accuracy (%) | 15.2 |
| Open Korean LLM - KorNAT-CKA | 14.85 | Normalized accuracy (%) | 7.3 |
| Open Korean LLM - KorNAT-Helpful | 40.12 | Normalized accuracy (%) | 6.8 |
| Open Ko-LLM Leaderboard | 28.22 | Average (%) | 5.7 |
| Open Korean LLM Leaderboard | 28.22 | Average Score (%) | 5.7 |
| Open Korean LLM - Ko-IFEval | 2.47 | Strict accuracy, prompt/instruction mean (%) | 4.2 |
Interactive version: theaggregate.ai/model?slug=test-llama2-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.