Qwen3 Max Thinking (Preview)
Available
2025-11-03
32,000 tokens
Other 开发的 AI 模型，具有出色的推理能力，适合多种 AI 应用场景。
Supported modalities:TextCode
Quick Overview
Text Generation3/10
Code Generation2/10
Reasoning8/10
Multimodal3/10
Benchmark Results
Scores from leading benchmark suites.
32.5%
artificial-analysis-intelligence
24.5%
artificial-analysis-coding
82.3%
artificial-analysis-math
Performance Metrics
Latency and throughput performance.
1000ms
P50 Latency
58.84
tokens/sec
Dive Deeper
Explore detailed analyses by topic.
Pricing Info
Feature support
Streaming
Tool calling
JSON mode