Bio-Saul-Dolphin-Beagle-Breadcrumbs: benchmark results
Provider: varox34. Released 2024-04-01. Access: Open.
Aggregate Rating 1294 ± 35, rank #8815 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - PubMedQA | 75.4 | Accuracy (%) | 72.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.39 | MC2 (%) (0-shot) | 34.3 |
| Open LLM Leaderboard v1 - MMLU | 50.74 | Accuracy (%) (5-shot) | 30 |
| Open LLM Leaderboard v1 - HellaSwag | 75.4 | Normalized accuracy (%) (10-shot) | 26.4 |
| Open LLM Leaderboard v1 - WinoGrande | 69.46 | Accuracy (%) (5-shot) | 23.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 48.63 | Normalized accuracy (%) (25-shot) | 23.4 |
| Open Medical LLM - MMLU Professional Medicine | 47.06 | Accuracy (%) | 19.5 |
| Open LLM Leaderboard v1 - GSM8K | 1.67 | Accuracy (%) (5-shot) | 17.9 |
| Open Medical LLM - MMLU College Biology | 50.69 | Accuracy (%) | 17.2 |
| Open Medical LLM | 46.73 | Average Accuracy (%) | 16.1 |
| Open Medical LLM - MMLU Clinical Knowledge | 49.43 | Accuracy (%) | 16.1 |
| Open Medical LLM - MMLU College Medicine | 38.73 | Accuracy (%) | 16.1 |
Interactive version: theaggregate.ai/model?slug=bio-saul-dolphin-beagle-breadcrumbs · How It Works · Data refreshed daily, snapshot 2026-11-08.