GPT-6.1 Sol (Medium) vs Mercury 2.5
Which is better for the money: GPT-6.1 Sol (Medium) 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 (Medium) scores 35.5 points higher (47.8 vs 12.3) but costs 1.7× as much to run the benchmark ($361 vs $218; both mid-range class). Pick GPT-6.1 Sol (Medium) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | GPT-6.1 Sol (Medium) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 47.8 | 12.3 | −74.3% Mercury 2.5 is 74.3% less intelligent |
| Total AA cost (lower is better) | $361.37 | $218.11 | −39.6% Mercury 2.5 is 39.6% cheaper |
| End-to-end time (lower is better) | 14.35s | 4.39s | −69.4% Mercury 2.5 is 69.4% 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 (Medium): 74.3% less intelligence, 39.6% less cost to run the AA benchmark, and 69.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Sol (Medium) 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 (Medium)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-medium/mercury-2-5 · Markdown: /api/v1/compare/gpt-6-1-sol-medium/mercury-2-5?format=md · llms.txt · agent skill