Mercury 2 vs Solar Mini 4
Which is better for the money: Mercury 2 by Inception or Solar Mini 4 by Upstage? 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
Solar Mini 4 scores 13.3 points higher (24.1 vs 10.8) but costs 4.8× as much to run the benchmark ($502 vs $105; premium vs mid-range cost classes). They are not alternatives at one budget: pick Solar Mini 4 when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | Mercury 2 | Solar Mini 4 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 10.8 | 24.1 | +123.1% Solar Mini 4 is 2.2× more intelligent |
| Total AA cost (lower is better) | $104.94 | $502.02 | +378.4% Solar Mini 4 is 4.8× more expensive |
| End-to-end time (lower is better) | 6.65s | 25.33s | +280.9% Solar Mini 4 is 280.9% slower |
| Price per 1M tokens (in / out) | $0.25 / $0.75 | $0.10 / $0.40 | |
| Input modalities | Text | Text |
Solar Mini 4 vs Mercury 2: 123.1% more intelligence, 378.4% more cost to run the AA benchmark, and 280.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- Solar Mini 4 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
Mercury 2Solar Mini 4Today'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/mercury-2/solar-mini4 · Markdown: /api/v1/compare/mercury-2/solar-mini4?format=md · llms.txt · agent skill