sitebunny-13B: benchmark results
Provider: Other.
Aggregate Rating 1369 ± 28, rank #7192 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 65.63 | Normalized accuracy (%) | 81.6 |
| Open Korean LLM - Ko-IFEval | 35.72 | Strict accuracy, prompt/instruction mean (%) | 73.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.21 | MC2 (%) (0-shot) | 67.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.14 | Normalized accuracy (%) (25-shot) | 61.5 |
| Open LLM Leaderboard v1 - HellaSwag | 83.64 | Normalized accuracy (%) (10-shot) | 60.3 |
| Open LLM Leaderboard v1 - WinoGrande | 76.72 | Accuracy (%) (5-shot) | 50.1 |
| Open Korean LLM - Ko-Winogrande | 59.75 | Accuracy (%) | 48.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 16.91 | Exact match, flexible extract (%) | 47.4 |
| Open LLM Leaderboard v1 - MMLU | 59.91 | Accuracy (%) (5-shot) | 46.3 |
| Open Korean LLM - KorNAT-Helpful | 46.2 | Normalized accuracy (%) | 42.8 |
| Open Korean LLM Leaderboard | 33.08 | Average Score (%) | 37.9 |
| Open LLM Leaderboard v1 - GSM8K | 9.4 | Accuracy (%) (5-shot) | 30 |
Interactive version: theaggregate.ai/model?slug=sitebunny-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.