Model Comparator

Compare up to four models using the same criteria.

Claude 4.1 Opus (Reasoning)
Anthropic
MiniMax-M2.5
MiniMax

Differences only

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

Model Comparator
Metrics	Claude 4.1 Opus (Reasoning) Anthropic	MiniMax-M2.5 MiniMax
Intelligence	22.8	22.8
Math	80.3	—
Speed	—	66.9 t/s
TTFT	—	1.46 s
Input · $ / 1M tokens	$15×50 relative to the lowest price among the compared models	Best: $0.30
Output · $ / 1M tokens	$75×62.5 relative to the lowest price among the compared models	Best: $1.20
Context window	200K	Best: 205K
Reasoning	Yes	Yes
Open weights	No	Yes

Intelligence

Claude 4.1 Opus (Reasoning): 22.8
MiniMax-M2.5: 22.8

Math

Claude 4.1 Opus (Reasoning): 80.3
MiniMax-M2.5: —

Speed

Claude 4.1 Opus (Reasoning): —
MiniMax-M2.5: 66.9 t/s

TTFT

Claude 4.1 Opus (Reasoning): —
MiniMax-M2.5: 1.46 s

Input · $ / 1M tokens

Claude 4.1 Opus (Reasoning): $15×50 relative to the lowest price among the compared models
MiniMax-M2.5: Best: $0.30

Output · $ / 1M tokens

Claude 4.1 Opus (Reasoning): $75×62.5 relative to the lowest price among the compared models
MiniMax-M2.5: Best: $1.20

Context window

Claude 4.1 Opus (Reasoning): 200K
MiniMax-M2.5: Best: 205K

Reasoning

Claude 4.1 Opus (Reasoning): Yes
MiniMax-M2.5: Yes

Open weights

Claude 4.1 Opus (Reasoning): No
MiniMax-M2.5: 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.

Claude 4.1 Opus (Reasoning)22.8 · $30
MiniMax-M2.522.8 · $0.525