Model Comparator

Compare up to four models using the same criteria.

Qwen3 235B A22B Thinking 2507
Qwen
Qwen3 Max (Preview)
Alibaba

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Qwen3 235B A22B Thinking 2507 Qwen	Qwen3 Max (Preview) Alibaba
Intelligence	Best: 12.7	12.6
Coding	22.1	—
Math	—	75
Agentic	1.3	—
Speed	—	57.4 t/s
TTFT	—	3.96 s
Input · $ / 1M tokens	Best: $0.45	$1.20×2.7 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $3.50	$6×1.7 relative to the lowest price among the compared models
Context window	128K	Best: 262K
Reasoning	Yes	No
Open weights	Yes	No

Intelligence

Qwen3 235B A22B Thinking 2507: Best: 12.7
Qwen3 Max (Preview): 12.6

Coding

Qwen3 235B A22B Thinking 2507: 22.1
Qwen3 Max (Preview): —

Math

Qwen3 235B A22B Thinking 2507: —
Qwen3 Max (Preview): 75

Agentic

Qwen3 235B A22B Thinking 2507: 1.3
Qwen3 Max (Preview): —

Speed

Qwen3 235B A22B Thinking 2507: —
Qwen3 Max (Preview): 57.4 t/s

TTFT

Qwen3 235B A22B Thinking 2507: —
Qwen3 Max (Preview): 3.96 s

Input · $ / 1M tokens

Qwen3 235B A22B Thinking 2507: Best: $0.45
Qwen3 Max (Preview): $1.20×2.7 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3 235B A22B Thinking 2507: Best: $3.50
Qwen3 Max (Preview): $6×1.7 relative to the lowest price among the compared models

Context window

Qwen3 235B A22B Thinking 2507: 128K
Qwen3 Max (Preview): Best: 262K

Reasoning

Qwen3 235B A22B Thinking 2507: Yes
Qwen3 Max (Preview): No

Open weights

Qwen3 235B A22B Thinking 2507: Yes
Qwen3 Max (Preview): No

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Qwen3 235B A22B Thinking 250712.7 · $1.21
Qwen3 Max (Preview)12.6 · $2.40