openbuddy-zephyr-7B-v14.1: benchmark results
Provider: OpenBuddy. Access: Open.
Aggregate Rating 1314 ± 29, rank #8460 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 63.44 | Normalized accuracy (%) | 62.8 |
| Open Korean LLM - KorNAT-Helpful | 46.75 | Normalized accuracy (%) | 48.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.84 | MC2 (%) (0-shot) | 46.2 |
| Open LLM Leaderboard v1 - MMLU | 56.21 | Accuracy (%) (5-shot) | 38.5 |
| Open LLM Leaderboard v1 - WinoGrande | 73.24 | Accuracy (%) (5-shot) | 31.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.13 | Normalized accuracy (%) (25-shot) | 26.7 |
| Open LLM Leaderboard v1 - HellaSwag | 75.02 | Normalized accuracy (%) (10-shot) | 25.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.61 | Exact match, flexible extract (%) | 24.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open LLM Leaderboard v1 - GSM8K | 4.7 | Accuracy (%) (5-shot) | 23.3 |
| Open Korean LLM - Ko-IFEval | 18.96 | Strict accuracy, prompt/instruction mean (%) | 14.8 |
| Open Korean LLM Leaderboard | 29.78 | Average Score (%) | 13.7 |
Interactive version: theaggregate.ai/model?slug=openbuddy-zephyr-7b-v14-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.