DeepSeek V4.1 Flash 1017 (Max) vs Mercury 2.5
Which is better for the money: DeepSeek V4.1 Flash 1017 (Max) by DeepSeek or Mercury 2.5 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 32.8 points higher (45.1 vs 12.3) but costs 2.0× as much to run the benchmark ($445 vs $218; both mid-range class). Pick DeepSeek V4.1 Flash 1017 (Max) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | DeepSeek V4.1 Flash 1017 (Max) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.1 | 12.3 | −72.7% Mercury 2.5 is 72.7% less intelligent |
| Total AA cost (lower is better) | $444.60 | $218.11 | −50.9% Mercury 2.5 is 50.9% cheaper |
| End-to-end time (lower is better) | 16.22s | 4.24s | −73.9% Mercury 2.5 is 73.9% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2.5 vs DeepSeek V4.1 Flash 1017 (Max): 72.7% less intelligence, 50.9% less cost to run the AA benchmark, and 73.9% 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 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek V4.1 Flash 1017 (Max)Mercury 2.5Today'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-2-5 · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017/mercury-2-5?format=md · llms.txt · agent skill