ModelBeat
Models/Qwen3.5-9B
All models
A
qwen/qwen3.5-9b

Qwen3.5-9B is Alibaba’s open-weights AI model, released Feb 24, 2026. It costs $0.10/M input and $0.15/M output tokens, and handles a 262K-token context window.

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.

Context
262K
Input
$0.10 / 1M
Output
$0.15 / 1M
Released
Feb 24, 2026
Modalities
textimagevideotext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen3.5-9B lands among all models tracked on Model Beat.

17.0
Intelligence Index
Epoch AI
17th percentile of tracked models
2.0
Coding Index
Epoch AI
2nd percentile of tracked models
24.0
Agentic Index
Epoch AI
24th percentile of tracked models

Reasoning

2 evals
GPQA Diamond80.6%

Graduate-level scientific reasoning

Humanity's Last Exam14.9%

Frontier of human expert knowledge

Coding

1 evals
SciCode27.5%

Scientific research coding

Agentic & Tools

2 evals
Terminal-Bench9.2%

Command-line agentic tasks

τ²-bench86.8%

Tool-agent-user reliability

Changelog

2
  • Qwen3.5-9B: Humanity's Last Exam improved from 13.3% to 14.9% (+12%)benchmark · Aug 6, 2026
  • Qwen3.5-9B (Alibaba) added to the tracker.tracked · Jun 22, 2026

Compare Qwen3.5-9B with

Frequently asked questions

What is Qwen3.5-9B?

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.

Who created Qwen3.5-9B?

Qwen3.5-9B is an AI model developed by Alibaba, part of the Qwen family, released Feb 24, 2026.

How much does Qwen3.5-9B cost?

Qwen3.5-9B is served from $0.10 per million input tokens and $0.15 per million output tokens (cheapest credible provider on OpenRouter: SiliconFlow).

What is Qwen3.5-9B's context window?

Qwen3.5-9B supports a context window of up to 262K tokens.

How does Qwen3.5-9B perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen3.5-9B scores 86.8% on τ²-bench, 80.6% on GPQA Diamond, 14.9% on Humanity's Last Exam.

Is Qwen3.5-9B open source?

Qwen3.5-9B is released with open weights (Open weights (restricted use)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 20, 2026.