GPT-5.6 Terra (Max) vs Mercury 2

Which is better for the money: GPT-5.6 Terra (Max) by OpenAI or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Trade-off

OpenAIGPT-5.6 Terra (Max)Off the frontier

Intelligence: 42.10
Total cost: $2501

InceptionMercury 2Off the frontier

Intelligence: 10.80
Total cost: $105

Verdict

Depends on your budget

GPT-5.6 Terra (Max) scores 31.3 points higher (42.1 vs 10.8) but costs 24× as much to run the benchmark ($2501 vs $105; flagship vs mid-range cost classes). They are not alternatives at one budget: pick GPT-5.6 Terra (Max) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.

Metric	GPT-5.6 Terra (Max)	Mercury 2	Difference
Intelligence (higher is better)	42.1	10.8	−74.3% Mercury 2 is 74.3% less intelligent
Total AA cost (lower is better)	$2,500.72	$104.94	−95.8% Mercury 2 is 95.8% cheaper
End-to-end time (lower is better)	107.91s	6.58s	−93.9% Mercury 2 is 93.9% faster
Price per 1M tokens (in / out)	$2.00 / $12.0	$0.25 / $0.75
Input modalities	Text, Image	Text

Mercury 2 vs GPT-5.6 Terra (Max): 74.3% less intelligence, 95.8% less cost to run the AA benchmark, and 93.9% faster end-to-end.

Open this matchup in the interactive picker GPT-5.6 Terra (Max): what beats it Mercury 2: what beats it

Today's Pareto frontier

Against the frontier

GPT-5.6 Terra (Max) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.

GPT-5.6 Terra (Max)Mercury 2Today'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/gpt-5-6-terra/mercury-2 · Markdown: /api/v1/compare/gpt-5-6-terra/mercury-2?format=md · llms.txt · agent skill