Skip to main content
AITier

Qwen3 235B A22B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3 235B A22B is a large language model developed by Alibaba, featuring a Mixture-of-Experts (MoE) architecture with 235 billion total parameters and 22 billion activated parameters. It achieves competitive results in benchmark evaluations of coding, math, general capabilities, and more, compared to other top-tier models.

Release Date
2025-04-28
Parameters
235.0B
Context Length
131K
Modalities
text

Capability Radar

33
general
23
coding
40
reasoning
39
scienceest.
70
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking351
19.0
AA
General Ranking286
38.0
AA
Math Reasoning227
39.0
AA
Reasoning32
79.0
LS
Science275
40.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA47.5%SR

Chemistry

SuperGPQA44.1%SR

Code

EvalPlus0.78 / 100SR
LiveCodeBench70.7%SR
Aider61.8%SR

Creativity

Arena Hard95.6%SR

Finance

MMLU87.8%SR
MMLU-Pro68.2%SR

General

MMLU-Redux87.4%SR
MMMLU86.7%SR
MBPP0.81 / 100SR
LiveBench77.1%SR
Include73.5%SR
MultiLF71.9%SR
BFCL70.8%SR
MultiPL-E65.9%SR

Language

BBH88.9%SR

Math

GSM8k94.4%SR
AIME 202485.7%SR
MGSM83.5%SR
AIME 202581.5%SR
MATH71.8%SR

Reasoning

CRUX-O0.79 / 100SR

AA Evaluation Indices

Math Index
23.7
Intelligence Index
17.0
Coding Index
14.0
Math 500
0.9
Mmlu Pro
0.8
Gpqa
0.6
Ifbench
0.4
Livecodebench
0.3
Aime
0.3
Scicode
0.3
Tau2
0.3
Aime 25
0.2
Terminalbench Hard
0.1
Hle
0.0
Lcr
0.0

LLM Stats Category Scores

Writing
100
Creativity
100
Language
80
Math
80
Reasoning
80
Tool Calling
70
Code
70
Finance
70
General
70
Healthcare
70
Legal
70
Biology
50
Chemistry
50
Physics
50
Economics
40

Pricing

Input Price$0.45 / 1M tokens
Output Price$1.8 / 1M tokens
Blended Price (3:1)$0.787 / 1M tokens

Speed

Tokens/sec64.1 tokens/s
Time to First Token1.24s
Time to Answer1.24s

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats