Model Comparator

Compare up to four models using the same criteria.

Qwen3 Max Thinking (Preview)
Alibaba
Claude 4 Opus (Non-reasoning)
Anthropic

Differences only

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

Model Comparator
Metrics	Qwen3 Max Thinking (Preview) Alibaba	Claude 4 Opus (Non-reasoning) Anthropic
Intelligence	16.3	Best: 16.6
Math	Best: 82.3	36.3
Speed	51.7 t/s	—
TTFT	4.03 s	—
Input · $ / 1M tokens	Best: $1.20	$15×12.5 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $6	$75×12.5 relative to the lowest price among the compared models
Context window	Best: 262K	200K
Reasoning	Yes	No
Open weights	No	No

Intelligence

Qwen3 Max Thinking (Preview): 16.3
Claude 4 Opus (Non-reasoning): Best: 16.6

Math

Qwen3 Max Thinking (Preview): Best: 82.3
Claude 4 Opus (Non-reasoning): 36.3

Speed

Qwen3 Max Thinking (Preview): 51.7 t/s
Claude 4 Opus (Non-reasoning): —

TTFT

Qwen3 Max Thinking (Preview): 4.03 s
Claude 4 Opus (Non-reasoning): —

Input · $ / 1M tokens

Qwen3 Max Thinking (Preview): Best: $1.20
Claude 4 Opus (Non-reasoning): $15×12.5 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3 Max Thinking (Preview): Best: $6
Claude 4 Opus (Non-reasoning): $75×12.5 relative to the lowest price among the compared models

Context window

Qwen3 Max Thinking (Preview): Best: 262K
Claude 4 Opus (Non-reasoning): 200K

Reasoning

Qwen3 Max Thinking (Preview): Yes
Claude 4 Opus (Non-reasoning): No

Open weights

Qwen3 Max Thinking (Preview): No
Claude 4 Opus (Non-reasoning): 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 Max Thinking (Preview)16.3 · $2.40
Claude 4 Opus (Non-reasoning)16.6 · $30