Qwen3 235B A22B 2507

Reasoning

Creator

Alibaba

Released

2025-07-25

Intelligence

29.5

Artificial Analysis Index

Coding

23.2

Artificial Analysis Index

In $/1M

$0.40

input tokens

Out $/1M

$2.15

output tokens

Blended $/1M

$0.84

3:1 blended

Speed

64

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
79
Humanity’s Last Exam
15
MMLU-Pro
84
SciCode
42
LiveCodeBench
79
MATH-500
98
AIME 2025
91
τ²-Bench (agentic)
53
Terminal-Bench Hard
14
IFBench
51
Via Artificial Analysis