Model Comparator

Compare up to four models using the same criteria.

GPT-5.6 Terra (Medium)
OpenAI
Claude Sonnet 4.6 (Non-reasoning, High)
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 Terra (Medium) OpenAI	Claude Sonnet 4.6 (Non-reasoning, High) Anthropic
Intelligence	30.1	30.1
Coding	Best: 64.7	63
Agentic	30.4	Best: 31.8
Speed	Best: 97.2 t/s	43.1 t/s
TTFT	1.48 s	Best: 1 s
Input · $ / 1M tokens	Best: $2	$3×1.5 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $12	$15×1.3 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	Yes	No
Open weights	No	No
Cost / task	$0.183	—

Intelligence

GPT-5.6 Terra (Medium): 30.1
Claude Sonnet 4.6 (Non-reasoning, High): 30.1

Coding

GPT-5.6 Terra (Medium): Best: 64.7
Claude Sonnet 4.6 (Non-reasoning, High): 63

Agentic

GPT-5.6 Terra (Medium): 30.4
Claude Sonnet 4.6 (Non-reasoning, High): Best: 31.8

Speed

GPT-5.6 Terra (Medium): Best: 97.2 t/s
Claude Sonnet 4.6 (Non-reasoning, High): 43.1 t/s

TTFT

GPT-5.6 Terra (Medium): 1.48 s
Claude Sonnet 4.6 (Non-reasoning, High): Best: 1 s

Input · $ / 1M tokens

GPT-5.6 Terra (Medium): Best: $2
Claude Sonnet 4.6 (Non-reasoning, High): $3×1.5 relative to the lowest price among the compared models

Output · $ / 1M tokens

GPT-5.6 Terra (Medium): Best: $12
Claude Sonnet 4.6 (Non-reasoning, High): $15×1.3 relative to the lowest price among the compared models

Context window

GPT-5.6 Terra (Medium): 1M
Claude Sonnet 4.6 (Non-reasoning, High): 1M

Reasoning

GPT-5.6 Terra (Medium): Yes
Claude Sonnet 4.6 (Non-reasoning, High): No

Open weights

GPT-5.6 Terra (Medium): No
Claude Sonnet 4.6 (Non-reasoning, High): No

Cost / task

GPT-5.6 Terra (Medium): $0.183
Claude Sonnet 4.6 (Non-reasoning, High): —

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 Terra (Medium)30.1 · $4.50
Claude Sonnet 4.6 (Non-reasoning, High)30.1 · $6