zephyr-7B-beta-KOR-OpenOrca-Platypus-1e-5: benchmark results

Provider: heegyu. Access: Open.

Aggregate Rating 1358 ± 43, rank #7478 of 10552 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-EQ-Bench17.19EQ-Bench score63.1
Open Korean LLM - KorNAT-Harmless62.67Normalized accuracy (%)48.4
Open Korean LLM - Ko-GSM8K (flexible extract)15.85Exact match, flexible extract (%)45.7
Open Korean LLM - KorNAT-Helpful46.33Normalized accuracy (%)44.8
Open Korean LLM Leaderboard33.75Average Score (%)43.6
Open Korean LLM - Ko-IFEval27.05Strict accuracy, prompt/instruction mean (%)41.3
Open Korean LLM - Ko-Winogrande57.85Accuracy (%)34.9
Open Korean LLM - KorNAT-CKA18.58Normalized accuracy (%)20.1
Open Korean LLM - Ko-GPQA-Diamond19.7Normalized accuracy (%)9.6

Interactive version: theaggregate.ai/model?slug=zephyr-7b-beta-kor-openorca-platypus-1e-5 · How It Works · Data refreshed daily, snapshot 2026-11-16.