Model Comparator

Compare up to four models using the same criteria.

GPT-6 Astra (Medium)
OpenAI
Claude Fable 5 (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 (Medium) OpenAI	Claude Fable 5 (batch) Anthropic
Intelligence	49.6	49.6
Coding	Best: 76.7	76.5
Agentic	46	Best: 50.7
Speed	43.8 t/s	—
TTFT	6.3 s	—
Input · $ / 1M tokens	$10	—
Output · $ / 1M tokens	$50	—
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	—
Cost / task	$1.54	—

Intelligence

GPT-6 Astra (Medium): 49.6
Claude Fable 5 (batch): 49.6

Coding

GPT-6 Astra (Medium): Best: 76.7
Claude Fable 5 (batch): 76.5

Agentic

GPT-6 Astra (Medium): 46
Claude Fable 5 (batch): Best: 50.7

Speed

GPT-6 Astra (Medium): 43.8 t/s
Claude Fable 5 (batch): —

TTFT

GPT-6 Astra (Medium): 6.3 s
Claude Fable 5 (batch): —

Input · $ / 1M tokens

GPT-6 Astra (Medium): $10
Claude Fable 5 (batch): —

Output · $ / 1M tokens

GPT-6 Astra (Medium): $50
Claude Fable 5 (batch): —

Context window

GPT-6 Astra (Medium): 1M
Claude Fable 5 (batch): 1M

Reasoning

GPT-6 Astra (Medium): Yes
Claude Fable 5 (batch): Yes

Open weights

GPT-6 Astra (Medium): No
Claude Fable 5 (batch): —

Cost / task

GPT-6 Astra (Medium): $1.54
Claude Fable 5 (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 (Medium)49.6 · $1.54

Not plotted for lack of data on these axes: Claude Fable 5 (batch).