StarEmpress-3x7B: benchmark results

Provider: Other.

Aggregate Rating 1458 ± 38, rank #3436 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K72.93Accuracy (%) (5-shot)98.3
Open LLM Leaderboard v1 - ARC Challenge71.16Normalized accuracy (%) (25-shot)88.2
Open LLM Leaderboard v1 - TruthfulQA MC268.25MC2 (%) (0-shot)87.3
Open LLM Leaderboard v1 - HellaSwag87.2Normalized accuracy (%) (10-shot)84.9
Open LLM Leaderboard v1 - MMLU65.52Accuracy (%) (5-shot)84.7
Open LLM Leaderboard v1 - WinoGrande82.08Accuracy (%) (5-shot)82.2

Interactive version: theaggregate.ai/model?slug=starempress-3x7b · How It Works · Data refreshed daily, snapshot 2026-11-08.