GPT-6.1 Sol (Max) vs Mercury 2.5
Which is better for the money: GPT-6.1 Sol (Max) by OpenAI or Mercury 2.5 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Sol (Max) scores 39.5 points higher (51.8 vs 12.3) but costs 5.0× as much to run the benchmark ($1082 vs $218; premium vs mid-range cost classes). They are not alternatives at one budget: pick GPT-6.1 Sol (Max) when you need intelligence above 12.3, and Mercury 2.5 when 12.3 is enough.
| Metric | GPT-6.1 Sol (Max) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 51.8 | 12.3 | −76.3% Mercury 2.5 is 76.3% less intelligent |
| Total AA cost (lower is better) | $1,081.55 | $218.11 | −79.8% Mercury 2.5 is 79.8% cheaper |
| End-to-end time (lower is better) | 220.48s | 4.39s | −98.0% Mercury 2.5 is 98.0% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2.5 vs GPT-6.1 Sol (Max): 76.3% less intelligence, 79.8% less cost to run the AA benchmark, and 98.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (Max) is on today's frontier: nothing is both smarter and cheaper.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-6.1 Sol (Max)Mercury 2.5Today'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-sol/mercury-2-5 · Markdown: /api/v1/compare/gpt-6-1-sol/mercury-2-5?format=md · llms.txt · agent skill