zephyr_tuning_v1: benchmark results
Provider: HuggingFace. Access: Open.
Unified ELO 1362 ± 17, rank #2160 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.18 | Normalized accuracy (%) | 77.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.86 | Exact match, flexible extract (%) | 43.8 |
| Open Korean LLM - Ko-IFEval | 25.99 | Strict accuracy, prompt/instruction mean (%) | 37.7 |
| Open Korean LLM - Ko-Winogrande | 57.62 | Accuracy (%) | 32.9 |
| Open Korean LLM Leaderboard | 30.83 | Average Score (%) | 22.1 |
| Open Ko-LLM Leaderboard | 30.83 | Average (%) | 22 |
| Open Korean LLM - KorNAT-Harmless | 60.83 | Normalized accuracy (%) | 19.7 |
| Open Korean LLM - KorNAT-CKA | 18.09 | Normalized accuracy (%) | 17.8 |
| Open Korean LLM - Ko-EQ-Bench | -1.3 | EQ-Bench score | 3.7 |
Interactive version: theaggregate.ai/model?slug=zephyr-tuning-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.