qwen2.5-7B-instruct-simpo: benchmark results

Provider: Alibaba. Access: Open.

Aggregate Rating 1502 ± 34, rank #2319 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Xlsum JA Rouge136.8Score (%)96.9
Open Japanese LLM - Xlsum JA RougeLsum29.22Score (%)94
Open Japanese LLM - Xlsum JA Bert Score JA F171.29Score (%)93.8
Open Japanese LLM - Xlsum JA Rouge211.07Score (%)82.5
Open Japanese LLM - SUM11.04Score (%)81.7
Open Japanese LLM - Jnli Exact Match84.35Score (%)65.5
Open Japanese LLM - Wiki PAS SET F17.05Score (%)57.2
Open Japanese LLM - Jsick Exact Match78.73Score (%)51.9
Open Japanese LLM - Wiki NER SET F15.31Score (%)51.2
Open Japanese LLM - Jsts Pearson88.02Score (%)49.3
Open Japanese LLM - HE65.93Score (%)48.3
Open Japanese LLM - Jmmlu Exact Match62.24Score (%)47.8

Interactive version: theaggregate.ai/model?slug=qwen2-5-7b-instruct-simpo · How It Works · Data refreshed daily, snapshot 2026-11-08.