Model Comparator

Compare up to four models using the same criteria.

GPT-5.6 Luna (High)
OpenAI
Claude Opus 4.6 (batch)
Anthropic

Differences only

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

Model Comparator
Metrics	GPT-5.6 Luna (High) OpenAI	Claude Opus 4.6 (batch) Anthropic
Intelligence	Best: 32.1	31.9
Coding	63.3	—
Agentic	34.6	—
Speed	115 t/s	—
TTFT	16.9 s	—
Input · $ / 1M tokens	$0.20	—
Output · $ / 1M tokens	$1.20	—
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	—
Cost / task	$0.044	—

Intelligence

GPT-5.6 Luna (High): Best: 32.1
Claude Opus 4.6 (batch): 31.9

Coding

GPT-5.6 Luna (High): 63.3
Claude Opus 4.6 (batch): —

Agentic

GPT-5.6 Luna (High): 34.6
Claude Opus 4.6 (batch): —

Speed

GPT-5.6 Luna (High): 115 t/s
Claude Opus 4.6 (batch): —

TTFT

GPT-5.6 Luna (High): 16.9 s
Claude Opus 4.6 (batch): —

Input · $ / 1M tokens

GPT-5.6 Luna (High): $0.20
Claude Opus 4.6 (batch): —

Output · $ / 1M tokens

GPT-5.6 Luna (High): $1.20
Claude Opus 4.6 (batch): —

Context window

GPT-5.6 Luna (High): 1M
Claude Opus 4.6 (batch): 1M

Reasoning

GPT-5.6 Luna (High): Yes
Claude Opus 4.6 (batch): Yes

Open weights

GPT-5.6 Luna (High): No
Claude Opus 4.6 (batch): —

Cost / task

GPT-5.6 Luna (High): $0.044
Claude Opus 4.6 (batch): —

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.

GPT-5.6 Luna (High)32.1 · $0.044

Not plotted for lack of data on these axes: Claude Opus 4.6 (batch).