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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Visual Maths - Measurement | 97.3 | Accuracy (%) | 95.9 |
| SnakeBench | 32.4 | TrueSkill Rating | 91.6 |
| AI for Education Visual Maths - Statistics and Probability | 57.14 | Accuracy (%) | 88.5 |
| AI for Education Pedagogy - Science | 91.8 | Accuracy (%) | 88.4 |
| ALL Bench LLM | 75 | Average Numeric Benchmark Score (%) | 88.2 |
| AI for Education Pedagogy - Primary | 92.02 | Accuracy (%) | 86.1 |
| InfoOps Bench | 79.7 | Integrity Score (% refused) | 83.8 |
| AI for Education Visual Maths - Number and Operations | 67.57 | Accuracy (%) | 81.8 |
| AI for Education Visual Maths | 76.79 | Accuracy (%) | 81.1 |
| Vals AI AIME | 92.5 | Accuracy (%) | 81.1 |
| AI for Education Pedagogy - Technology | 83.96 | Accuracy (%) | 80.5 |
| AI for Education Visual Maths - Geometry | 73.08 | Accuracy (%) | 79.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-flash · How It Works · Data refreshed daily, snapshot 2026-09-05.