Dolly_Shygmalion-6B-Dev_V8P2: benchmark results

Provider: Databricks. Access: Open.

Aggregate Rating 1166 ± 15, rank #9793 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Mathematics32Accuracy (%)53.7
MMLU-by-task - Abstract Algebra29Accuracy (%)45.4
MMLU-by-task - Global Facts32Accuracy (%)44.3
MMLU-by-task - Security Studies43.27Accuracy (%)44
MMLU-by-task - High School Mathematics26.3Accuracy (%)40
MMLU-by-task - Professional Law30.64Accuracy (%)39.7
MMLU-by-task - Econometrics27.19Accuracy (%)39.6
MMLU-by-task - International Law43.8Accuracy (%)35.8
MMLU-by-task - High School European History30.91Accuracy (%)34.3
MMLU-by-task - College Medicine30.64Accuracy (%)34.2
MMLU-by-task - Nutrition33.01Accuracy (%)34.2
MMLU-by-task - Prehistory32.72Accuracy (%)34

Interactive version: theaggregate.ai/model?slug=dolly-shygmalion-6b-dev-v8p2 · How It Works · Data refreshed daily, snapshot 2026-11-08.