Qwen3.5 27B

Non-reasoning

Creator

Alibaba

Released

2026-02-24

Intelligence

37.2

Artificial Analysis Index

Coding

33.4

Artificial Analysis Index

In $/1M

$0.30

input tokens

Out $/1M

$2.60

output tokens

Blended $/1M

$0.88

3:1 blended

Speed

91

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
84
Humanity’s Last Exam
13
MMLU-Pro
SciCode
37
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
87
Terminal-Bench Hard
32
IFBench
47
Via Artificial Analysis