Qwen Plus 0728 (thinking) vs Qwen: Qwen3 30B A3B Instruct 2507
Compare Qwen Plus 0728 (thinking) and Qwen: Qwen3 30B A3B Instruct 2507, both from Qwen, context windows of 1.0M vs 131K, tested across 37 shared challenges.
Our Verdict
Qwen Plus 0728 (thinking)
Qwen: Qwen3 30B A3B Instruct 2507Runner-up
No community votes yet. On paper, Qwen Plus 0728 (thinking) has the edge — newer, bigger context window.
Qwen: Qwen3 30B A3B Instruct 2507 is 5.0x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Qwen Plus 0728 (thinking)
Input
$0.40
Output
$4.00
Qwen: Qwen3 30B A3B Instruct 2507
Input
$0.20
2.0× cheaper
Output
$0.80
5.0× cheaper
Qwen: Qwen3 30B A3B Instruct 2507 is cheaper on both — 2.0× input, 5.0× output
Writing DNA
Style Comparison
Similarity
75%
Qwen: Qwen3 30B A3B Instruct 2507 uses 3.1x more emoji
Qwen Plus 0728 (thinking)
Qwen: Qwen3 30B A3B Instruct 2507
54%Vocabulary55%
15wSentence Length18w
0.36Hedging0.52
7.0Bold6.7
4.6Lists4.3
0.34Emoji1.04
0.94Headings0.92
0.09Transitions0.11
Based on 18 + 22 text responses
Research
What we learned reading every model
FAQ
