cydinfo-llama3-8B-lora-v01: benchmark results
Provider: Other. Access: Open.
Unified ELO 1470 ± 17, rank #1378 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 40.33 | Strict accuracy, prompt/instruction mean (%) | 82.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM Leaderboard | 39.69 | Average Score (%) | 73.4 |
| Open Ko-LLM Leaderboard | 39.69 | Average (%) | 73.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.07 | Exact match, flexible extract (%) | 70.7 |
| Open Korean LLM - Ko-EQ-Bench | 15.67 | EQ-Bench score | 60.9 |
| Open Korean LLM - Ko-Winogrande | 60.77 | Accuracy (%) | 57.3 |
| Open Korean LLM - KorNAT-CKA | 23.27 | Normalized accuracy (%) | 44.1 |
| Open Korean LLM - KorNAT-Helpful | 45.48 | Normalized accuracy (%) | 37.1 |
| Open Korean LLM - KorNAT-Harmless | 61.32 | Normalized accuracy (%) | 27 |
Interactive version: theaggregate.ai/model?slug=cydinfo-llama3-8b-lora-v01 · How It Works · Data refreshed daily, snapshot 2026-09-19.