Qwen2.5-Math-7B-Instruct — benchmark results

Provider: Alibaba. Access: Open.

Unified ELO 1298 ± 29, rank #1494 of 1716 rated models, from 69 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MATH Level 558.08Score99.6
Open Japanese LLM - ALT E TO J Bleu JA60.89Score (%)98.1
Open Japanese LLM - Xlsum JA Bleu JA14.76Score (%)94.7
U-MATH - Sequences & Series51.95Accuracy (%)54.5
Open Japanese LLM - Jsick Exact Match78.71Score (%)51.7
U-MATH - Precalculus76.25Accuracy (%)51.5
U-MATH45.45Accuracy (%)45.5
Open Japanese LLM - MR76.6Score (%)43
U-MATH - Multivariable Calculus38.76Accuracy (%)42.4
U-MATH - Integral Calculus22.12Accuracy (%)36.4
Open Japanese LLM - CG1Score (%)34.1
U-MATH - Algebra71.67Accuracy (%)33.3

Interactive version: aibenchmarks.dev/model?slug=qwen2-5-math-7b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-09.