Alpaca_QLoRA_test: benchmark results
Provider: Other. Access: Open.
Unified ELO 1451 ± 17, rank #1517 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 51.23 | Normalized accuracy (%) | 89.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - KorNAT-Harmless | 66.1 | Normalized accuracy (%) | 84.5 |
| Open Korean LLM - Ko-IFEval | 39.39 | Strict accuracy, prompt/instruction mean (%) | 80.9 |
| Open Korean LLM - Ko-EQ-Bench | 24.23 | EQ-Bench score | 69.7 |
| Open Ko-LLM Leaderboard | 37.53 | Average (%) | 62.8 |
| Open Korean LLM Leaderboard | 37.53 | Average Score (%) | 62.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 23.43 | Exact match, flexible extract (%) | 56.4 |
| Open Korean LLM - Ko-Winogrande | 55.96 | Accuracy (%) | 23.7 |
| Open Korean LLM - KorNAT-CKA | 18.84 | Normalized accuracy (%) | 20.7 |
Interactive version: theaggregate.ai/model?slug=alpaca-qlora-test · How It Works · Data refreshed daily, snapshot 2026-09-19.