Sky-T1-32B-Flash: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1569 ± 32, rank #1422 of 10916 rated models, from 52 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MedPRMBench (Step Probability)65.4PRMScore (%): mean of the F1 for erroneous steps and the F1 100
Open Japanese LLM Leaderboard66.5Average Score (%)92.8
Open Japanese LLM - Jsts Spearman87.9Score (%)91.6
Open Japanese LLM - CG62.25Score (%)91.5
Open Japanese LLM - Jamp Exact Match70.4Score (%)91.5
Open Japanese LLM - Jmmlu Exact Match74.78Score (%)88.9
Open Japanese LLM - NLI80.45Score (%)88.5
Open Japanese LLM - Jnli Exact Match88.7Score (%)88.2
Open Japanese LLM - Wiki Dependency SET F140.97Score (%)87.7
Open Japanese LLM - HE77.16Score (%)87.5
Open Japanese LLM - Wikicorpus J TO E Comet Wmt2276.31Score (%)86.8
Open Japanese LLM - RC91.82Score (%)86.5

Interactive version: theaggregate.ai/model?slug=sky-t1-32b-flash · How It Works · Data refreshed daily, snapshot 2026-11-08.