Qwen2.5-14B-Instinct-RP: benchmark results

Provider: Alibaba. Access: Open.

Aggregate Rating 1555 ± 35, rank #1625 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - CG61.45Score (%)90
Open Japanese LLM - Jsts Pearson90.24Score (%)87.5
Open Japanese LLM - Mbpp Pylint Check95.58Score (%)86.1
Open Japanese LLM Leaderboard65.13Average Score (%)84.4
Open Japanese LLM - NLI79.35Score (%)83.4
Open Japanese LLM - RC91.6Score (%)82.7
Open Japanese LLM - Jnli Exact Match86.48Score (%)81.2
Open Japanese LLM - Jamp Exact Match68.1Score (%)81.1
Open Japanese LLM - Wikicorpus J TO E Bleu EN11.58Score (%)80.6
Open Japanese LLM - Jsts Spearman87.56Score (%)80
Open Japanese LLM - Wiki NER SET F110.62Score (%)79.2
Open Japanese LLM - Jcommonsenseqa Exact Match95.62Score (%)79.1

Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-instinct-rp · How It Works · Data refreshed daily, snapshot 2026-11-08.