Skip to main content

Qwen3 235B A22B 2507 (Reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3-235B-A22B-Thinking-2507 is a state-of-the-art thinking-enabled Mixture-of-Experts (MoE) model with 235B total parameters (22B activated). It features 94 layers, 128 experts (8 activated), and supports 262K native context length. This version delivers significantly improved reasoning performance, achieving state-of-the-art results among open-source thinking models on logical reasoning, mathematics, science, coding, and academic benchmarks. Key enhancements include markedly better general capabilities (instruction following, tool usage, text generation), enhanced 256K long-context understanding, and increased thinking depth. The model supports only thinking mode with automatic <think> tag inclusion.

Release Date
2025-07-25
Parameters
235.0B
Context Length
262K
Modalities
text

Capability Radar

70
general
0
coding
70
reasoning
68
scienceest.
60
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)87.8%SR
Multi-IF80.6%SR
TAU-bench Retail67.8%SR
Tau2 Airline58.0%SR

Code

CFEval2134.00 / 10000SR

Communication

Tau2 Retail71.9%SR
Tau2 Telecom45.6%SR

Creativity

Creative Writing v386.1%SR

General

Include81.0%SR
Arena-Hard v279.7%SR
BFCL-v371.9%SR

Language

MMLU-Redux93.8%SR
MMLU-Pro84.4%SR
MMLU-ProX81.0%SR

Math

AIME 202592.3%SR
HMMT2583.9%SR
LiveBench 2024112578.4%SR
PolyMATH60.1%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)81.1%SR
LiveCodeBench v674.1%SR
SuperGPQA64.9%SR
TAU-bench Airline46.0%SR
OJBench32.5%SR
Humanity's Last Exam18.2%SR

Writing

WritingBench88.3%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Instruction Following
80
Language
80
Legal
80
Structured Output
80
Finance
80
Healthcare
80
Biology
80
Creativity
80
Writing
80
Chat
70
Math
70
Physics
70
Reasoning
70
General
70
Agents
70
Chemistry
70
Communication
70
Multimodal
60
Spatial Reasoning
60
Economics
60
Tool Calling
60
Vision
40

Pricing

Input Price$0.23 / 1M tokens
Output Price$2.3 / 1M tokens
Blended Price (3:1)$0.305 / 1M tokens
Cache Read Price$0.05 / 1M tokens

Speed

Tokens/sec153.9
Time to First Token0.74s
Time to Answer13.74s

Provider Price Ranking

Provider Price Ranking

6 providers

Cheapest: TensorXMost Expensive: Jiekou.AI
ProviderInputOutput
1TensorXCheapest
$0.072
$0.464
2OpenRouter
$0.14
$0.8
3Kilo Gateway
$0.14
$0.8
4AlibabaPRIMARY
$0.23
$2.3
5NanoGPT
$0.3
$0.5
6Jiekou.AI
$0.3
$3

Compare pricing across different API providers for this model.

External Sources