Qwen 3.5 Plus — benchmark results

Alibaba's flagship Qwen 3.5 Plus API tier with thinking and non-thinking modes. Provider: Alibaba. Released 2026-02-16. Access: API.

Unified ELO 1719 ± 27, rank #243 of 1776 rated models, from 49 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Pedagogy - Science95.08Accuracy (%)100
ClawProBench64.19Final Score (self-reported)96.4
AI for Education Visual Maths - Number and Operations72.97Accuracy (%)95.8
AI for Education Pedagogy - Maths90.48Accuracy (%)94.5
AI for Education Visual Maths - Statistics and Probability57.14Accuracy (%)94.2
AI for Education Pedagogy - Secondary88.36Accuracy (%)93.9
AI for Education Pedagogy88.88Accuracy (%)93.6
AI for Education Visual Maths80.17Accuracy (%)91.7
AI for Education Visual Maths - Geometry77.69Accuracy (%)91.7
AI for Education Pedagogy - Technology85.85Accuracy (%)90.5
AI for Education Visual Reasoning - pattern completion (linear)83.8Accuracy (%)90.3
AI for Education Pedagogy - Social studies86.36Accuracy (%)88.6

Interactive version: theaggregate.ai/model?slug=qwen-3-5-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.