Nano GPT logo
NanoGPT
Provider logo

Qwen 3 235b A22B

qwen/qwen3-235b-a22b
BackTry Model
Provider logo

Qwen 3 235b A22B

qwen/qwen3-235b-a22b
BackTry Model

Qwen 3 235b is a 235b model with 22B active parameters. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.

Added Apr 29, 2025

Model weights

Context Window

41.0K

Max Output

32.8K

Avg output tokens (7d)

912 tokens

42%

Input Price (Auto)

$0.071/1M

Output Price (Auto)

$0.46/1M

Cache Read (Auto)

$0.036/1M

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

10.8

Better than 34% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

61.3%

Better than 38% of models compared

HLE

Humanity's Last Exam

4.2%

Better than 18% of models compared

IFBench

Instruction-following benchmark

36.6%

Better than 30% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

27.2%

Better than 33% of models compared

AA-LCR

Long context reasoning evaluation

0.0%

Better than 6% of models compared

Coding

SciCode

Python programming for scientific computing

29.9%

Better than 42% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

6.1%

Better than 34% of models compared

LiveCodeBench

Contamination-free coding benchmark

34.3%

Better than 41% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

23.7%

Better than 25% of models compared

AIME

American Invitational Mathematics Examination

32.7%

Better than 60% of models compared

Math-500

Diverse mathematical problem solving benchmark

90.2%

Better than 64% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

76.2%

Better than 53% of models compared

Last updated Aug 16, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Qwen 3 235b A22B with similar models from the same provider or model family.

Qwen 3 235b A22B 2507 Thinking

Qwen/Qwen3-235B-A22B-Thinking-2507

The thinking version of Qwen 3 235b A22B 2507, with enhanced reasoning capabilities and step-by-step problem solving.

Qwen 3 235b A22B 2507

Qwen/Qwen3-235B-A22B-Instruct-2507

Qwen 3 235b A22B Instruct 2507 the updated version of Qwen3 235B A22B, with significant improvements in performance. This model is non-thinking.

Qwen 3 235b A22B

Qwen/Qwen3-235B-A22B

Qwen 3 235b is a 235b model with 22B active parameters. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.

Qwen3 VL 235B A22B Instruct

Qwen/Qwen3-VL-235B-A22B-Instruct

Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts/diagrams, and multi‑image context.

Qwen 3.6 35B A3B Uncensored

qwen/qwen3.6-35b-a3b-uncensored

Qwen 3.6 35B A3B Uncensored is an NVFP4 open-weight mixture-of-experts model LoRA-tuned for fewer refusals across chat, coding, tool use, and multimodal tasks.

Qwen 3.8 27B Uncensored

qwen/qwen3.8-27b-uncensored

Qwen 3.8 27B Uncensored is an NVFP4 open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, tool use, and long-context work.