GPT-6.1 Terra (Max) vs Mercury 2
Which is better for the money: GPT-6.1 Terra (Max) by OpenAI or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Terra (Max) scores 37.3 points higher (48.1 vs 10.8) but costs 5.2× as much to run the benchmark ($909 vs $175; premium vs mid-range cost classes). They are not alternatives at one budget: pick GPT-6.1 Terra (Max) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | GPT-6.1 Terra (Max) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 48.1 | 10.8 | −77.5% Mercury 2 is 77.5% less intelligent |
| Total AA cost (lower is better) | $909.01 | $174.51 | −80.8% Mercury 2 is 80.8% cheaper |
| End-to-end time (lower is better) | 83.46s | 8.06s | −90.3% Mercury 2 is 90.3% faster |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-6.1 Terra (Max): 77.5% less intelligence, 80.8% less cost to run the AA benchmark, and 90.3% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
GPT-6.1 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-6-1-terra/mercury-2 · Markdown: /api/v1/compare/gpt-6-1-terra/mercury-2?format=md · llms.txt · agent skill