llama3-pre1-pre2-ds-lora3: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1322 ± 17, rank #2381 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 22.75 | Strict accuracy, prompt/instruction mean (%) | 24.3 |
| Open Korean LLM - KorNAT-CKA | 17.43 | Normalized accuracy (%) | 14.8 |
| Open Korean LLM - Ko-Winogrande | 53.67 | Accuracy (%) | 13.3 |
| Open Korean LLM Leaderboard | 29.41 | Average Score (%) | 11.9 |
| Open Ko-LLM Leaderboard | 29.41 | Average (%) | 11.7 |
| Open Korean LLM - KorNAT-Helpful | 41 | Normalized accuracy (%) | 9.8 |
| Open Korean LLM - KorNAT-Harmless | 59.64 | Normalized accuracy (%) | 7.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.08 | Exact match, flexible extract (%) | 4.8 |
Interactive version: theaggregate.ai/model?slug=llama3-pre1-pre2-ds-lora3 · How It Works · Data refreshed daily, snapshot 2026-09-19.