BeagSake-7B: benchmark results
shadowml's BeagSake 7B, a LazyMergekit merge of their BeagleSempra-7B and WestBeagle-7B models. Provider: shadowml. Released 2024-03-01. Access: Open.
Aggregate Rating 1453 ± 14, rank #979 of 1656 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 75.05 | Normalized accuracy (%) | 97.1 |
| Open LLM Leaderboard v1 - GSM8K | 71.8 | Accuracy (%) (5-shot) | 96.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 72.27 | MC2 (%) (0-shot) | 93.3 |
| YALL Nous Leaderboard | 57.53 | Average | 92.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.44 | Normalized accuracy (%) (25-shot) | 92 |
| Open Korean LLM - KorNAT-Helpful | 51.93 | Normalized accuracy (%) | 91.8 |
| Open LLM Leaderboard v1 - HellaSwag | 88.39 | Normalized accuracy (%) (10-shot) | 91.4 |
| Open Chinese LLM - TruthfulQA MC | 61.95 | Accuracy (%) | 89.6 |
| Open Korean LLM Leaderboard | 41.72 | Average Score (%) | 83.5 |
| Open Ko-LLM Leaderboard | 41.72 | Average (%) | 83.4 |
| Open LLM Leaderboard v1 - MMLU | 65.23 | Accuracy (%) (5-shot) | 83.2 |
| Open LLM Leaderboard v1 - WinoGrande | 82.16 | Accuracy (%) (5-shot) | 82.7 |
Interactive version: theaggregate.ai/model?slug=beagsake-7b · How It Works · Data refreshed daily, snapshot 2026-10-20.