huozi3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1452 ± 33, rank #3674 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU70.61Accuracy (%) (5-shot)94.2
Open LLM Leaderboard v1 - WinoGrande82.16Accuracy (%) (5-shot)82.7
Open LLM Leaderboard v1 - HellaSwag86Normalized accuracy (%) (10-shot)78
Open LLM Leaderboard v1 - ARC Challenge65.02Normalized accuracy (%) (25-shot)68.8
Open LLM Leaderboard v1 - GSM8K54.59Accuracy (%) (5-shot)66.3
Open LLM Leaderboard v1 - TruthfulQA MC249.45MC2 (%) (0-shot)44.8

Interactive version: theaggregate.ai/model?slug=huozi3 · How It Works · Data refreshed daily, snapshot 2026-11-08.