ModelBeat
Models/Qwen 3.5 Flash (hosted 35B-A3B)
All models
A

Alibaba: Qwen 3.5 Flash (hosted 35B-A3B)

qwen-3-5-flash-hosted-35b-a3b

Qwen 3.5 Flash (hosted 35B-A3B) is Alibaba’s AI model, released Feb 25, 2026.

Context
Input
/ 1M
Output
/ 1M
Released
Feb 25, 2026
Modalities

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen 3.5 Flash (hosted 35B-A3B) lands among all models tracked on Model Beat.

16.0
Intelligence Index
Epoch AI
16th percentile of tracked models
6.0
Coding Index
Epoch AI
6th percentile of tracked models

Reasoning

2 evals
GPQA Diamond83.8%

Graduate-level scientific reasoning

SimpleQA Verified19.8%

Factual accuracy & hallucination

Coding

1 evals
WebDev Arena1237

Human-rated web development

Math

3 evals
AIME 2024/202585.6%

Olympiad-qualifier math

FrontierMath6.2%

Research-level math problems

FrontierMath Tier 40.0%

Hardest research math

Compare Qwen 3.5 Flash (hosted 35B-A3B) with

Frequently asked questions

What is Qwen 3.5 Flash (hosted 35B-A3B)?

Qwen 3.5 Flash (hosted 35B-A3B) is a Qwen-family AI model, from Alibaba, released Feb 25, 2026.

Who created Qwen 3.5 Flash (hosted 35B-A3B)?

Qwen 3.5 Flash (hosted 35B-A3B) is an AI model developed by Alibaba, part of the Qwen family, released Feb 25, 2026.

How does Qwen 3.5 Flash (hosted 35B-A3B) perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen 3.5 Flash (hosted 35B-A3B) scores 83.8% on GPQA Diamond, 85.6% on AIME 2024/2025, 6.2% on FrontierMath.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.