DeepSeek V4.1 Flash (Non-reasoning) vs Mercury 2.5
Which is better for the money: DeepSeek V4.1 Flash (Non-reasoning) 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 (Non-reasoning) scores 12.4 points higher (24.7 vs 12.3) but costs 1.1× as much to run the benchmark ($239 vs $218; both mid-range class). Pick DeepSeek V4.1 Flash (Non-reasoning) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | DeepSeek V4.1 Flash (Non-reasoning) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.7 | 12.3 | −50.2% Mercury 2.5 is 50.2% less intelligent |
| Total AA cost (lower is better) | $238.91 | $218.11 | −8.7% Mercury 2.5 is 8.7% cheaper |
| End-to-end time (lower is better) | 2.72s | 4.24s | +55.9% Mercury 2.5 is 55.9% slower |
| 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 (Non-reasoning): 50.2% less intelligence, 8.7% less cost to run the AA benchmark, and 55.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4.1 Flash (Non-reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- 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 (Non-reasoning)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-non-reasoning/mercury-2-5 · Markdown: /api/v1/compare/deepseek-v4-1-flash-non-reasoning/mercury-2-5?format=md · llms.txt · agent skill