Claude Fable 5.1 (High, Default Fallback) vs GPT-5 mini (High)

Which is better for the money: Claude Fable 5.1 (High, Default Fallback) by Anthropic or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.

Trade-off

AnthropicClaude Fable 5.1 (High, Default Fallback)Off the frontier

Intelligence: 51.20
Total cost: $5242

OpenAIGPT-5 mini (High)Off the frontier

Intelligence: 16.80
Total cost: $189

Verdict

Depends on your budget

Claude Fable 5.1 (High, Default Fallbac… scores 34.4 points higher (51.2 vs 16.8) but costs 28× as much to run the benchmark ($5242 vs $189; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Fable 5.1 (High, Default Fallbac… when you need intelligence above 16.8, and GPT-5 mini (High) when 16.8 is enough.

Metric	Claude Fable 5.1 (High, Default Fallback)	GPT-5 mini (High)	Difference
Intelligence (higher is better)	51.2	16.8	−67.2% GPT-5 mini (High) is 67.2% less intelligent
Total AA cost (lower is better)	$5,241.59	$188.66	−96.4% GPT-5 mini (High) is 96.4% cheaper
End-to-end time (lower is better)	26.71s	67.32s	+152.0% GPT-5 mini (High) is 152.0% slower
Price per 1M tokens (in / out)	$10.0 / $50.0	$0.25 / $2.00
Input modalities	Text, Image	Text, Image

GPT-5 mini (High) vs Claude Fable 5.1 (High, Default Fallback): 67.2% less intelligence, 96.4% less cost to run the AA benchmark, and 152.0% slower end-to-end.

Open this matchup in the interactive picker Claude Fable 5.1 (High, Default Fallback): what beats it GPT-5 mini (High): what beats it

Today's Pareto frontier

Against the frontier

Claude Fable 5.1 (High, Default Fallback) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.

Claude Fable 5.1 (High, Default Fallback)GPT-5 mini (High)Today's Pareto frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-fable-5-1-high/gpt-5-mini · Markdown: /api/v1/compare/claude-fable-5-1-high/gpt-5-mini?format=md · llms.txt · agent skill