Qwen3.5 397B A17B

Reasoning

Creator

Alibaba

Released

2026-02-16

Intelligence

45.0

Artificial Analysis Index

Coding

41.3

Artificial Analysis Index

In $/1M

$0.60

input tokens

Out $/1M

$3.60

output tokens

Blended $/1M

$1.35

3:1 blended

Speed

52

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
89
Humanity’s Last Exam
27
MMLU-Pro
SciCode
42
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
96
Terminal-Bench Hard
41
IFBench
79
Via Artificial Analysis