GPT-6 Sol (Medium) vs Mercury 2
Which is better for the money: GPT-6 Sol (Medium) by OpenAI or Mercury 2 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 Sol (Medium) scores 29.0 points higher (39.8 vs 10.8) but costs 4.0× as much to run the benchmark ($416 vs $105; both mid-range class). They are not alternatives at one budget: pick GPT-6 Sol (Medium) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | GPT-6 Sol (Medium) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 39.8 | 10.8 | −72.9% Mercury 2 is 72.9% less intelligent |
| Total AA cost (lower is better) | $416.32 | $104.94 | −74.8% Mercury 2 is 74.8% cheaper |
| End-to-end time (lower is better) | Not reported | 8.08s | — not comparable |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-6 Sol (Medium): 72.9% less intelligence, 74.8% less cost to run the AA benchmark, and end-to-end time not fully reported.
Today's Pareto frontier
Against the frontier
- GPT-6 Sol (Medium) 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 (High) scores 37.80 for $94.1.
GPT-6 Sol (Medium)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-sol-medium/mercury-2 · Markdown: /api/v1/compare/gpt-6-sol-medium/mercury-2?format=md · llms.txt · agent skill