GPT-6.1 Terra (Xhigh) vs Mercury 2
Which is better for the money: GPT-6.1 Terra (Xhigh) 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 (Xhigh) scores 34.6 points higher (45.4 vs 10.8) but costs 2.1× as much to run the benchmark ($365 vs $175; both mid-range class). Pick GPT-6.1 Terra (Xhigh) when the extra intelligence is worth the premium, otherwise Mercury 2.
| Metric | GPT-6.1 Terra (Xhigh) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.4 | 10.8 | −76.2% Mercury 2 is 76.2% less intelligent |
| Total AA cost (lower is better) | $364.95 | $174.51 | −52.2% Mercury 2 is 52.2% cheaper |
| End-to-end time (lower is better) | 18.82s | 8.06s | −57.2% Mercury 2 is 57.2% 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 (Xhigh): 76.2% less intelligence, 52.2% less cost to run the AA benchmark, and 57.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- 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 (Xhigh)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-xhigh/mercury-2 · Markdown: /api/v1/compare/gpt-6-1-terra-xhigh/mercury-2?format=md · llms.txt · agent skill