DeepSeek V4.1 Flash 1017 (Max) vs Mercury 2
Which is better for the money: DeepSeek V4.1 Flash 1017 (Max) by DeepSeek 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
DeepSeek V4.1 Flash 1017 (Max) scores 34.3 points higher (45.1 vs 10.8) but costs 4.2× as much to run the benchmark ($445 vs $105; both mid-range class). They are not alternatives at one budget: pick DeepSeek V4.1 Flash 1017 (Max) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | DeepSeek V4.1 Flash 1017 (Max) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.1 | 10.8 | −76.1% Mercury 2 is 76.1% less intelligent |
| Total AA cost (lower is better) | $444.60 | $104.94 | −76.4% Mercury 2 is 76.4% cheaper |
| End-to-end time (lower is better) | 15.97s | 6.65s | −58.4% Mercury 2 is 58.4% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs DeepSeek V4.1 Flash 1017 (Max): 76.1% less intelligence, 76.4% less cost to run the AA benchmark, and 58.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4.1 Flash 1017 (Max) 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.
DeepSeek V4.1 Flash 1017 (Max)Mercury 2Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-1-flash-1017/mercury-2 · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017/mercury-2?format=md · llms.txt · agent skill