Model Comparator

Compare up to four models using the same criteria.

GPT-6 Astra (Low)
OpenAI
Claude Opus 4.8 (batch)
Anthropic

Differences only

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

Model Comparator
Metrics	GPT-6 Astra (Low) OpenAI	Claude Opus 4.8 (batch) Anthropic
Intelligence	Best: 43.3	41.8
Coding	Best: 75.7	74.3
Agentic	38.8	Best: 41.9
Speed	42.2 t/s	—
TTFT	2.88 s	—
Input · $ / 1M tokens	$10×4 relative to the lowest price among the compared models	Best: $2.50
Output · $ / 1M tokens	$50×4 relative to the lowest price among the compared models	Best: $12.50
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	—
Cost / task	$1.42	—

Intelligence

GPT-6 Astra (Low): Best: 43.3
Claude Opus 4.8 (batch): 41.8

Coding

GPT-6 Astra (Low): Best: 75.7
Claude Opus 4.8 (batch): 74.3

Agentic

GPT-6 Astra (Low): 38.8
Claude Opus 4.8 (batch): Best: 41.9

Speed

GPT-6 Astra (Low): 42.2 t/s
Claude Opus 4.8 (batch): —

TTFT

GPT-6 Astra (Low): 2.88 s
Claude Opus 4.8 (batch): —

Input · $ / 1M tokens

GPT-6 Astra (Low): $10×4 relative to the lowest price among the compared models
Claude Opus 4.8 (batch): Best: $2.50

Output · $ / 1M tokens

GPT-6 Astra (Low): $50×4 relative to the lowest price among the compared models
Claude Opus 4.8 (batch): Best: $12.50

Context window

GPT-6 Astra (Low): 1M
Claude Opus 4.8 (batch): 1M

Reasoning

GPT-6 Astra (Low): Yes
Claude Opus 4.8 (batch): Yes

Open weights

GPT-6 Astra (Low): No
Claude Opus 4.8 (batch): —

Cost / task

GPT-6 Astra (Low): $1.42
Claude Opus 4.8 (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-6 Astra (Low)43.3 · $20
Claude Opus 4.8 (batch)41.8 · $5