GPT-5.6 Luna (High) vs Mercury 2
Which is better for the money: GPT-5.6 Luna (High) by OpenAI or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-5.6 Luna (High) scores 21.3 points higher (32.1 vs 10.8) but costs 1.0× as much to run the benchmark ($108 vs $105; both mid-range class). Pick GPT-5.6 Luna (High) when the extra intelligence is worth the premium, otherwise Mercury 2.
| Metric | GPT-5.6 Luna (High) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.1 | 10.8 | −66.4% Mercury 2 is 66.4% less intelligent |
| Total AA cost (lower is better) | $108.15 | $104.94 | −3.0% Mercury 2 is 3.0% cheaper |
| End-to-end time (lower is better) | 12.33s | 6.58s | −46.6% Mercury 2 is 46.6% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-5.6 Luna (High): 66.4% less intelligence, 3.0% less cost to run the AA benchmark, and 46.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- 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 Luna (High)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-luna-high/mercury-2 · Markdown: /api/v1/compare/gpt-5-6-luna-high/mercury-2?format=md · llms.txt · agent skill