Qwen3 Max Thinking (Preview)

Alibaba

ReasoningProprietary

Analysis of Alibaba's Qwen3 Max Thinking (Preview) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Nov 03, 2025
Window: 262k

PricingPer 1M tokens

Input: $1.2
Output: $6
Blended 3:1: $2.4

Capabilities

Speed: 54 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 4.18 ms
500 token response: 50.69 s

Benchmarks

Reasoning: ●●○○○
Math: ●●●●○
Coding: ●○○○○
MMLU Pro: 82.4%
GPQA: 77.6%
HLE: 12.0%
SciCode: 38.7%
AIME: 82.3%
LiveCodeBench: 53.5%

Analysis of Alibaba's Qwen3 Max Thinking (Preview) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.