Model Comparator

Compare up to four models using the same criteria.

Qwen3 Max Thinking
Alibaba
MiniMax-M2.1
MiniMax

Differences only

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

Model Comparator
Metrics	Qwen3 Max Thinking Alibaba	MiniMax-M2.1 MiniMax
Intelligence	Best: 21.3	20.9
Math	—	82.7
Speed	—	59.3 t/s
TTFT	—	1.56 s
Input · $ / 1M tokens	—	$0.30
Output · $ / 1M tokens	—	$1.20
Context window	Best: 256K	205K
Reasoning	Yes	Yes
Open weights	No	Yes

Intelligence

Qwen3 Max Thinking: Best: 21.3
MiniMax-M2.1: 20.9

Math

Qwen3 Max Thinking: —
MiniMax-M2.1: 82.7

Speed

Qwen3 Max Thinking: —
MiniMax-M2.1: 59.3 t/s

TTFT

Qwen3 Max Thinking: —
MiniMax-M2.1: 1.56 s

Input · $ / 1M tokens

Qwen3 Max Thinking: —
MiniMax-M2.1: $0.30

Output · $ / 1M tokens

Qwen3 Max Thinking: —
MiniMax-M2.1: $1.20

Context window

Qwen3 Max Thinking: Best: 256K
MiniMax-M2.1: 205K

Reasoning

Qwen3 Max Thinking: Yes
MiniMax-M2.1: Yes

Open weights

Qwen3 Max Thinking: No
MiniMax-M2.1: Yes

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.

MiniMax-M2.120.9 · $0.525

Not plotted for lack of data on these axes: Qwen3 Max Thinking.