ShortKing-3B-v0.3: benchmark results

Provider: Other.

Aggregate Rating 1177 ± 42, rank #9730 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag70.72Normalized accuracy (%) (10-shot)20.9
Open LLM Leaderboard v1 - WinoGrande66.93Accuracy (%) (5-shot)20.9
Open LLM Leaderboard v1 - ARC Challenge40.96Normalized accuracy (%) (25-shot)17.3
Open LLM Leaderboard v1 - GSM8K1.21Accuracy (%) (5-shot)16
Open LLM Leaderboard v1 - MMLU26.21Accuracy (%) (5-shot)11.7
Open LLM Leaderboard v1 - TruthfulQA MC238.78MC2 (%) (0-shot)9.2

Interactive version: theaggregate.ai/model?slug=shortking-3b-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.