Qwen3 235B A22B
Qwen3 235B A22B is a large language model from Alibaba with a Mixture-of-Experts (MoE) architecture, containing 235 billion total parameters and 22 billion active parameters. Achieves competitive results on coding, math, general capabilities, and other benchmarks compared to other top models.
Key Specifications
Parameters
235.0B
Context
128.0K
Release Date
April 28, 2025
Average Score
76.2%
Timeline
Key dates in the model's history
Announcement / Last Update
April 28, 2025
Today
October 5, 2026
Technical Specifications
Parameters
235.0B
Training Tokens
36.0T tokens
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Pricing & Availability
Input (per 1M tokens)
$0.20
Output (per 1M tokens)
$0.60
Max Input Tokens
128.0K
Max Output Tokens
128.0K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Benchmark Results
Model performance metrics across various tests and benchmarks
General Knowledge
Tests on general knowledge and understanding
MMLU
Accuracy • Self-reported
Programming
Programming skills tests
MBPP
Accuracy • Self-reported
Mathematics
Mathematical problems and computations
GSM8k
Accuracy • Self-reported
MATH
Accuracy • Self-reported
MGSM
Accuracy • Self-reported
Reasoning
Logical reasoning and analysis
GPQA
Accuracy • Self-reported
Other Tests
Specialized benchmarks
Arena Hard
Accuracy • Self-reported
BBH
Accuracy • Self-reported
MMMLU
Accuracy • Self-reported
Aider
Pass@2 • Self-reported
AIME 2024
Pass@64 • Self-reported
AIME 2025
Pass@64 • Self-reported
BFCL
v3 • Self-reported
CRUX-O
Score • Self-reported
EvalPlus
Score • Self-reported
Include
Score • Self-reported
LiveBench
Accuracy • Self-reported
LiveCodeBench
v5 • Self-reported
MMLU-Pro
Accuracy • Self-reported
MMLU-Redux
Accuracy • Self-reported
MultiLF
Accuracy • Self-reported
MultiPL-E
Score • Self-reported
SuperGPQA
Accuracy • Self-reported
License & Metadata
License
apache-2.0
Announcement Date
April 28, 2025
Last Updated
April 28, 2025
Articles about Qwen3 235B A22B
Similar Models
All ModelsQwen3-235B-A22B-Thinking-2507
Alibaba
235.0B
Best score:0.8 (GPQA)
Released:Jul 2025
Price:$0.30/1M tokens
Qwen3-235B-A22B-Instruct-2507
Alibaba
235.0B
Best score:0.8 (GPQA)
Released:Jul 2025
Price:$0.15/1M tokens
Qwen3-Coder 480B A35B Instruct
Alibaba
480.0B
Best score:0.8 (TAU)
Released:Jan 2025
Qwen3.5 122B A10B
Alibaba
122.0B
Best score:0.9 (GPQA)
Released:Mar 2026
Qwen3 Max Thinking
Alibaba
1.0T
Best score:0.9 (GPQA)
Released:Feb 2026
Price:$1.20/1M tokens
Qwen3 Max
Alibaba
Best score:0.6 (GPQA)
Released:Dec 2025
Qwen2.5-Coder 7B Instruct
Alibaba
7.0B
Best score:0.9 (HumanEval)
Released:Sep 2024
Qwen2.5 72B Instruct
Alibaba
72.7B
Best score:0.9 (HumanEval)
Released:Sep 2024
Price:$1.20/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.