GPT-5 mini (High) vs Mercury 2
Which is better for the money: GPT-5 mini (High) by OpenAI or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-5 mini (High) scores 6.0 points higher (16.8 vs 10.8) but costs 1.8× as much to run the benchmark ($189 vs $105; both mid-range class). Pick GPT-5 mini (High) when the extra intelligence is worth the premium, otherwise Mercury 2.
| Metric | GPT-5 mini (High) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.8 | 10.8 | −35.7% Mercury 2 is 35.7% less intelligent |
| Total AA cost (lower is better) | $188.66 | $104.94 | −44.4% Mercury 2 is 44.4% cheaper |
| End-to-end time (lower is better) | 58.72s | 6.65s | −88.7% Mercury 2 is 88.7% faster |
| Price per 1M tokens (in / out) | $0.25 / $2.00 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-5 mini (High): 35.7% less intelligence, 44.4% less cost to run the AA benchmark, and 88.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
- 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 mini (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-mini/mercury-2 · Markdown: /api/v1/compare/gpt-5-mini/mercury-2?format=md · llms.txt · agent skill