Model Comparator

Compare up to four models using the same criteria.

Claude Opus 4.8 (Max)
Anthropic
Claude Opus 4.7 (Max)
Anthropic

Differences only

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

Model Comparator
Metrics	Claude Opus 4.8 (Max) Anthropic	Claude Opus 4.7 (Max) Anthropic
Intelligence	Best: 41.8	40.7
Coding	Best: 74.3	73.6
Agentic	Best: 41.9	38.6
Speed	Best: 58.8 t/s	48.1 t/s
TTFT	51.5 s	Best: 27.9 s
Input · $ / 1M tokens	$5	$5
Output · $ / 1M tokens	$25	$25
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$4.08	—

Intelligence

Claude Opus 4.8 (Max): Best: 41.8
Claude Opus 4.7 (Max): 40.7

Coding

Claude Opus 4.8 (Max): Best: 74.3
Claude Opus 4.7 (Max): 73.6

Agentic

Claude Opus 4.8 (Max): Best: 41.9
Claude Opus 4.7 (Max): 38.6

Speed

Claude Opus 4.8 (Max): Best: 58.8 t/s
Claude Opus 4.7 (Max): 48.1 t/s

TTFT

Claude Opus 4.8 (Max): 51.5 s
Claude Opus 4.7 (Max): Best: 27.9 s

Input · $ / 1M tokens

Claude Opus 4.8 (Max): $5
Claude Opus 4.7 (Max): $5

Output · $ / 1M tokens

Claude Opus 4.8 (Max): $25
Claude Opus 4.7 (Max): $25

Context window

Claude Opus 4.8 (Max): 1M
Claude Opus 4.7 (Max): 1M

Reasoning

Claude Opus 4.8 (Max): Yes
Claude Opus 4.7 (Max): Yes

Open weights

Claude Opus 4.8 (Max): No
Claude Opus 4.7 (Max): No

Cost / task

Claude Opus 4.8 (Max): $4.08
Claude Opus 4.7 (Max): —

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 Opus 4.8 (Max)41.8 · $10
Claude Opus 4.7 (Max)40.7 · $10