Qwen3.5 2B

Reasoning

Creator

Alibaba

Released

2026-03-02

Intelligence

16.3

Artificial Analysis Index

Coding

3.5

Artificial Analysis Index

In $/1M

$0.02

input tokens

Out $/1M

$0.10

output tokens

Blended $/1M

$0.04

3:1 blended

Speed

0

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
46
Humanity’s Last Exam
2
MMLU-Pro
SciCode
3
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
69
Terminal-Bench Hard
4
IFBench
31
Via Artificial Analysis