Re-ultiima-14B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1544 ± 35, rank #1778 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Wiki Coreference SET F19.56Score (%)93.1
Open Japanese LLM - Wiki PAS SET F18.17Score (%)78.2
Open Japanese LLM - Janli Exact Match82.78Score (%)77.5
Open Japanese LLM - ALT E TO J Comet Wmt2290.79Score (%)73.7
Open Japanese LLM - Jcommonsenseqa Exact Match95.35Score (%)71.6
Open Japanese LLM - Niilc Char F153.1Score (%)70.8
Open Japanese LLM - Jemhopqa Char F157.5Score (%)70.3
Open Japanese LLM - Xlsum JA Bleu JA2.83Score (%)70.1
Open Japanese LLM - CG47.39Score (%)69.7
Open Japanese LLM Leaderboard63.04Average Score (%)67.1
Open Japanese LLM - ALT E TO J Bert Score JA F186.25Score (%)66.6
Open Japanese LLM - Mbpp Pylint Check72.49Score (%)65.5

Interactive version: theaggregate.ai/model?slug=re-ultiima-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.