Qwen3 235B A22B 2507 (Reasoning)

Alibaba

ReasoningApache 2.0

Analysis of Alibaba's Qwen3 235B A22B 2507 (Reasoning) 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: Jul 25, 2025
Window: 256k

PricingPer 1M tokens

Input: $0.4
Output: $2.15
Blended 3:1: $0.8375

Capabilities

Speed: 70 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 2.85 ms
500 token response: 38.32 s

Benchmarks

Reasoning: ●○○○○
Math: ●●●●●
Coding: ●○○○○
MMLU Pro: 84.3%
GPQA: 79.0%
HLE: 15.0%
SciCode: 42.4%
AIME: 94.0%
MATH 500: 98.4%
LiveCodeBench: 78.8%
HumanEval: 97.7%

Analysis of Alibaba's Qwen3 235B A22B 2507 (Reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.