bloom: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1222 ± 36, rank #9463 of 10916 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HellaSwag74.4Accuracy (%)40.1
Open LLM Leaderboard v1 - HellaSwag76.41Normalized accuracy (%) (10-shot)28.6
Open LLM Leaderboard v1 - WinoGrande72.06Accuracy (%) (5-shot)28.1
BoolQ70.4Accuracy (%)27.3
Open LLM Leaderboard v1 - GSM8K6.9Accuracy (%) (5-shot)26.1
Open LLM Leaderboard v1 - ARC Challenge50.43Normalized accuracy (%) (25-shot)24.7
Open LLM Leaderboard v1 - MMLU30.85Accuracy (%) (5-shot)17
GSM8K9.5Accuracy (%)14
Open LLM Leaderboard v1 - TruthfulQA MC239.76MC2 (%) (0-shot)11.9

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