HelpSteer-filtered-7B: benchmark results

Provider: Weyaxi. Access: Open.

Aggregate Rating 1394 ± 34, rank #6377 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU63.52Accuracy (%) (5-shot)61.3
Open LLM Leaderboard v1 - HellaSwag83.32Normalized accuracy (%) (10-shot)57.9
Open LLM Leaderboard v1 - GSM8K33.43Accuracy (%) (5-shot)49.5
Open LLM Leaderboard v1 - WinoGrande76.01Accuracy (%) (5-shot)45.4
Open LLM Leaderboard v1 - ARC Challenge59.56Normalized accuracy (%) (25-shot)43.8
Open LLM Leaderboard v1 - TruthfulQA MC241.11MC2 (%) (0-shot)16.1

Interactive version: theaggregate.ai/model?slug=helpsteer-filtered-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.