Llama 3 8B Cv Swap V0.1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1426 ± 17, rank #1697 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.91 | Exact match, flexible extract (%) | 72.3 |
| Open Korean LLM - KorNAT-Harmless | 63.94 | Normalized accuracy (%) | 68.6 |
| Open Korean LLM - KorNAT-CKA | 27.23 | Normalized accuracy (%) | 68.3 |
| Open Korean LLM - Ko-EQ-Bench | 22.05 | EQ-Bench score | 67.3 |
| Open Korean LLM - Ko-IFEval | 31.6 | Strict accuracy, prompt/instruction mean (%) | 60.6 |
| Open Korean LLM Leaderboard | 35.11 | Average Score (%) | 49.7 |
| Open Ko-LLM Leaderboard | 35.11 | Average (%) | 49.6 |
| Open Korean LLM - KorNAT-Helpful | 45.27 | Normalized accuracy (%) | 35.6 |
| Open Korean LLM - Ko-Winogrande | 55.09 | Accuracy (%) | 18.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-cv-swap-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.