Model Comparator

Compare up to four models using the same criteria.

Claude Opus 4.8 (batch)
Anthropic
GPT-5.6 Terra (Max)
OpenAI

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 (batch) Anthropic	GPT-5.6 Terra (Max) OpenAI
Intelligence	41.8	Best: 42.1
Coding	74.3	Best: 76.7
Agentic	41.9	Best: 43.2
Speed	—	135 t/s
TTFT	—	112 s
Input · $ / 1M tokens	$2.50×1.3 relative to the lowest price among the compared models	Best: $2
Output · $ / 1M tokens	$12.50	Best: $12
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	—	No
Cost / task	—	$1.40

Intelligence

Claude Opus 4.8 (batch): 41.8
GPT-5.6 Terra (Max): Best: 42.1

Coding

Claude Opus 4.8 (batch): 74.3
GPT-5.6 Terra (Max): Best: 76.7

Agentic

Claude Opus 4.8 (batch): 41.9
GPT-5.6 Terra (Max): Best: 43.2

Speed

Claude Opus 4.8 (batch): —
GPT-5.6 Terra (Max): 135 t/s

TTFT

Claude Opus 4.8 (batch): —
GPT-5.6 Terra (Max): 112 s

Input · $ / 1M tokens

Claude Opus 4.8 (batch): $2.50×1.3 relative to the lowest price among the compared models
GPT-5.6 Terra (Max): Best: $2

Output · $ / 1M tokens

Claude Opus 4.8 (batch): $12.50
GPT-5.6 Terra (Max): Best: $12

Context window

Claude Opus 4.8 (batch): 1M
GPT-5.6 Terra (Max): 1M

Reasoning

Claude Opus 4.8 (batch): Yes
GPT-5.6 Terra (Max): Yes

Open weights

Claude Opus 4.8 (batch): —
GPT-5.6 Terra (Max): No

Cost / task

Claude Opus 4.8 (batch): —
GPT-5.6 Terra (Max): $1.40

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 (batch)41.8 · $5
GPT-5.6 Terra (Max)42.1 · $4.50