Model Comparator

Compare up to four models using the same criteria.

Qwen3 Max Thinking (Preview)
Alibaba
Gemini 2.5 Pro
Google

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	Gemini 2.5 Pro Google
Intelligence	Best: 16.3	16.1
Coding	—	33.3
Math	82.3	Best: 87.7
Agentic	—	1.6
Speed	51.7 t/s	Best: 118 t/s
TTFT	Best: 4.03 s	20.9 s
Input · $ / 1M tokens	Best: $1.20	$1.25
Output · $ / 1M tokens	Best: $6	$10×1.7 relative to the lowest price among the compared models
Context window	262K	Best: 1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$0.33

Intelligence

Qwen3 Max Thinking (Preview): Best: 16.3
Gemini 2.5 Pro: 16.1

Coding

Qwen3 Max Thinking (Preview): —
Gemini 2.5 Pro: 33.3

Math

Qwen3 Max Thinking (Preview): 82.3
Gemini 2.5 Pro: Best: 87.7

Agentic

Qwen3 Max Thinking (Preview): —
Gemini 2.5 Pro: 1.6

Speed

Qwen3 Max Thinking (Preview): 51.7 t/s
Gemini 2.5 Pro: Best: 118 t/s

TTFT

Qwen3 Max Thinking (Preview): Best: 4.03 s
Gemini 2.5 Pro: 20.9 s

Input · $ / 1M tokens

Qwen3 Max Thinking (Preview): Best: $1.20
Gemini 2.5 Pro: $1.25

Output · $ / 1M tokens

Qwen3 Max Thinking (Preview): Best: $6
Gemini 2.5 Pro: $10×1.7 relative to the lowest price among the compared models

Context window

Qwen3 Max Thinking (Preview): 262K
Gemini 2.5 Pro: Best: 1M

Reasoning

Qwen3 Max Thinking (Preview): Yes
Gemini 2.5 Pro: Yes

Open weights

Qwen3 Max Thinking (Preview): No
Gemini 2.5 Pro: No

Cost / task

Qwen3 Max Thinking (Preview): —
Gemini 2.5 Pro: $0.33

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
Gemini 2.5 Pro16.1 · $3.44