llama3-diverce-ver1.6: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1330 ± 17, rank #2347 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-IFEval | 23.89 | Strict accuracy, prompt/instruction mean (%) | 28.8 |
| Open Korean LLM - Ko-Winogrande | 56.27 | Accuracy (%) | 25.3 |
| Open Korean LLM Leaderboard | 29.87 | Average Score (%) | 14.6 |
| Open Ko-LLM Leaderboard | 29.87 | Average (%) | 14.5 |
| Open Korean LLM - KorNAT-CKA | 16.63 | Normalized accuracy (%) | 12.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.68 | Exact match, flexible extract (%) | 10 |
| Open Korean LLM - KorNAT-Harmless | 59.87 | Normalized accuracy (%) | 9.9 |
| Open Korean LLM - KorNAT-Helpful | 40.98 | Normalized accuracy (%) | 9.7 |
| Open Korean LLM - Ko-EQ-Bench | -2.57 | EQ-Bench score | 3 |
Interactive version: theaggregate.ai/model?slug=llama3-diverce-ver1-6 · How It Works · Data refreshed daily, snapshot 2026-09-19.