llama3-diverce-ver1.0: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1340 ± 18, rank #2283 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - Ko-IFEval | 23.54 | Strict accuracy, prompt/instruction mean (%) | 27.3 |
| Open Korean LLM - Ko-Winogrande | 56.35 | Accuracy (%) | 25.8 |
| Open Korean LLM Leaderboard | 30.3 | Average Score (%) | 18.3 |
| Open Ko-LLM Leaderboard | 30.3 | Average (%) | 18.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.14 | Exact match, flexible extract (%) | 12.3 |
| Open Korean LLM - KorNAT-Helpful | 41.48 | Normalized accuracy (%) | 12.1 |
| Open Korean LLM - KorNAT-CKA | 16.06 | Normalized accuracy (%) | 11.6 |
| Open Korean LLM - KorNAT-Harmless | 59.91 | Normalized accuracy (%) | 10.4 |
| Open Korean LLM - Ko-EQ-Bench | -1.33 | EQ-Bench score | 3.6 |
Interactive version: theaggregate.ai/model?slug=llama3-diverce-ver1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.