Llama 2 7B Exo Test V1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1350 ± 17, rank #2239 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 58.64 | Accuracy (%) | 40.3 |
| Open Korean LLM - KorNAT-CKA | 19.71 | Normalized accuracy (%) | 26.3 |
| Open Korean LLM - Ko-IFEval | 22.84 | Strict accuracy, prompt/instruction mean (%) | 24.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 3.64 | Exact match, flexible extract (%) | 21.7 |
| Open Ko-LLM Leaderboard | 30.71 | Average (%) | 21 |
| Open Korean LLM Leaderboard | 30.71 | Average Score (%) | 21 |
| Open Korean LLM - KorNAT-Helpful | 42.95 | Normalized accuracy (%) | 19.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.19 | Normalized accuracy (%) | 6.4 |
| Open Korean LLM - KorNAT-Harmless | 59.39 | Normalized accuracy (%) | 6.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-exo-test-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.