mergekit-model_stock-qndyhny: benchmark results

Provider: MergeKit Community. Access: Open.

Aggregate Rating 1559 ± 35, rank #1575 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Jsts Pearson90.34Score (%)90.3
Open Japanese LLM - Jsts Spearman87.8Score (%)88.1
Open Japanese LLM - Jcommonsenseqa Exact Match95.89Score (%)88
Open Japanese LLM - ALT E TO J Comet Wmt2290.96Score (%)85.5
Open Japanese LLM - MT84.94Score (%)85
Open Japanese LLM - EL58.06Score (%)84.6
Open Japanese LLM Leaderboard65.14Average Score (%)84.6
Open Japanese LLM - Wikicorpus E TO J Comet Wmt2284.2Score (%)84.3
Open Japanese LLM - Wiki Coreference SET F17.55Score (%)83.9
Open Japanese LLM - Jmmlu Exact Match72.66Score (%)82.8
Open Japanese LLM - CG58.03Score (%)82.5
Open Japanese LLM - Commonsensemoralja Exact Match90.71Score (%)82.5

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