s1-32B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1555 ± 36, rank #1626 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Wiki NER SET F115.93Score (%)96.9
Open Japanese LLM - Wiki Coreference SET F111.09Score (%)95.2
Open Japanese LLM - NLI81.38Score (%)94.1
Open Japanese LLM - CG63.05Score (%)92.7
Open Japanese LLM - FA31.29Score (%)91.8
Open Japanese LLM - Wiki PAS SET F110.63Score (%)91.1
Open Japanese LLM Leaderboard65.96Average Score (%)91.1
Open Japanese LLM - Mbpp Pylint Check96.39Score (%)89.1
Open Japanese LLM - Jmmlu Exact Match74.7Score (%)88.7
Open Japanese LLM - Jnli Exact Match88.82Score (%)88.7
Open Japanese LLM - Jsick Exact Match84.49Score (%)88.5
Open Japanese LLM - HE77.07Score (%)86.8

Interactive version: theaggregate.ai/model?slug=s1-32b · How It Works · Data refreshed daily, snapshot 2026-11-08.