Qwen 3.5 Flash: benchmark results

Provider: Alibaba. Released 2026-02-16. Access: API.

Unified ELO 1632 ± 1, rank #174 of 1392 rated models, from 97 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Visual Maths - Measurement97.3Accuracy (%)95.9
SnakeBench32.4TrueSkill Rating91.6
AI for Education Visual Maths - Statistics and Probability57.14Accuracy (%)88.5
AI for Education Pedagogy - Science91.8Accuracy (%)88.4
ALL Bench LLM75Average Numeric Benchmark Score (%)88.2
AI for Education Pedagogy - Primary92.02Accuracy (%)86.1
InfoOps Bench79.7Integrity Score (% refused)83.8
AI for Education Visual Maths - Number and Operations67.57Accuracy (%)81.8
AI for Education Visual Maths76.79Accuracy (%)81.1
Vals AI AIME92.5Accuracy (%)81.1
AI for Education Pedagogy - Technology83.96Accuracy (%)80.5
AI for Education Visual Maths - Geometry73.08Accuracy (%)79.7

Interactive version: theaggregate.ai/model?slug=qwen-3-5-flash · How It Works · Data refreshed daily, snapshot 2026-09-05.