Llama 2 13B Instruct Y24 V2: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1378 ± 17, rank #2066 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 58.96 | Accuracy (%) | 43 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 12.74 | Exact match, flexible extract (%) | 39.6 |
| Open Korean LLM - Ko-IFEval | 26.06 | Strict accuracy, prompt/instruction mean (%) | 37.9 |
| Open Korean LLM - KorNAT-Helpful | 44.65 | Normalized accuracy (%) | 31.6 |
| Open Korean LLM Leaderboard | 32.19 | Average Score (%) | 31.6 |
| Open Ko-LLM Leaderboard | 32.19 | Average (%) | 31.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.74 | Normalized accuracy (%) | 18.7 |
| Open Korean LLM - KorNAT-CKA | 15.21 | Normalized accuracy (%) | 8.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-instruct-y24-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.