Qwen

Qwen3 VL 8B Thinking

by Qwentext+image->text1 endpoint
Neura Intelligence Index
48.7/ 100
Rank
#183
Confidence
medium
Benchmarks
7(18% coverage)

Overview

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
ImageText
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
32.8K tokens
Tokenizer
Qwen3
Uptime (24h)
10000.0%
Parameters
9000000000B
License
apache_2_0Open Weights
Country
🇨🇳CN
Release Date
September 22, 202512mo

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

general

BenchmarkScoreSource
SimpleQA
49.6
verified

math

BenchmarkScoreSource
AIME 2025
80.3
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
69.9
verified

multimodal

BenchmarkScoreSource
MMMU-Pro
60.4
verified
CharXiv Reasoning
53
verified
ScreenSpot Pro
46.6
verified

agent

BenchmarkScoreSource
OSWorld
33.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.18
Output$2.10
Added
October 14, 2025
Last synced 9/20/2026