karakuri-lm-32B-thinking-2501-exp: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1570 ± 36, rank #1405 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - RC92.89Score (%)99.5
Open Japanese LLM - CG67.27Score (%)98.7
Open Japanese LLM - Jnli Exact Match90.26Score (%)98
Open Japanese LLM - Wiki NER SET F115.93Score (%)96.9
Open Japanese LLM - Jmmlu Exact Match76.28Score (%)96.4
Open Japanese LLM - Jsem Exact Match80.87Score (%)96.4
Open Japanese LLM Leaderboard67.81Average Score (%)96.4
Open Japanese LLM - HE78.27Score (%)95.9
Open Japanese LLM - ALT E TO J Comet Wmt2291.19Score (%)93.3
Open Japanese LLM - FA31.44Score (%)92.8
Open Japanese LLM - Mbpp Pylint Check97.79Score (%)92.7
Open Japanese LLM - Kuci Exact Match83.68Score (%)92.2

Interactive version: theaggregate.ai/model?slug=karakuri-lm-32b-thinking-2501-exp · How It Works · Data refreshed daily, snapshot 2026-11-08.