Qwen3 VL 8B

Reasoning

Creator

Alibaba

Released

2025-10-14

Intelligence

16.7

Artificial Analysis Index

Coding

9.8

Artificial Analysis Index

In $/1M

$0.18

input tokens

Out $/1M

$2.10

output tokens

Blended $/1M

$0.66

3:1 blended

Speed

136

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
58
Humanity’s Last Exam
3
MMLU-Pro
75
SciCode
22
LiveCodeBench
35
MATH-500
AIME 2025
31
τ²-Bench (agentic)
23
Terminal-Bench Hard
4
IFBench
40
Via Artificial Analysis