dolly-v2-3B (Publisher: databricks): benchmark results

Provider: Databricks.

Aggregate Rating 1112 ± 37, rank #10597 of 10916 rated models, from 5 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K1.06Accuracy (%) (5-shot)15.4
Open LLM Leaderboard v1 - WinoGrande59.43Accuracy (%) (5-shot)12.6
Open LLM Leaderboard v1 - MMLU24.7Accuracy (%) (5-shot)4.8
Open LLM Leaderboard v1 - ARC Challenge25.26Normalized accuracy (%) (25-shot)4.6
Open LLM Leaderboard v1 - HellaSwag26.55Normalized accuracy (%) (10-shot)3.4

Interactive version: theaggregate.ai/model?slug=dolly-v2-3b-publisher-databricks · How It Works · Data refreshed daily, snapshot 2026-11-08.