BioMistral-Zephyr-Beta-SLERP: benchmark results

Provider: Avignon Univ. Released 2024-02-01. Access: Open.

Aggregate Rating 1390 ± 34, rank #6521 of 10916 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Medical LLM - PubMedQA76.6Accuracy (%)85.4
Open LLM Leaderboard v1 - HellaSwag84.13Normalized accuracy (%) (10-shot)64
Open LLM Leaderboard v1 - TruthfulQA MC254.6MC2 (%) (0-shot)63
Open LLM Leaderboard v1 - ARC Challenge62.12Normalized accuracy (%) (25-shot)56.1
Open LLM Leaderboard v1 - WinoGrande76.64Accuracy (%) (5-shot)49.6
Open LLM Leaderboard v1 - MMLU60.63Accuracy (%) (5-shot)49.1
Open Medical LLM - MedQA (USMLE)50.43Accuracy (%)34.4
Open Medical LLM - MMLU Professional Medicine64.71Accuracy (%)32
Open Medical LLM - MMLU Anatomy54.81Accuracy (%)30.5
Open Medical LLM60.65Average Accuracy (%)30.2
Open Medical-LLM Leaderboard (BenchmarkList)60.65Medical average (%)30
Open Medical LLM - MedMCQA45.8Accuracy (%)29.7

Interactive version: theaggregate.ai/model?slug=biomistral-zephyr-beta-slerp · How It Works · Data refreshed daily, snapshot 2026-11-08.