DeepSeek V4 Pro 0813 (Non-reasoning) vs Mercury 2.5
Which is better for the money: DeepSeek V4 Pro 0813 (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 Pro 0813 (Non-reasoning) scores 8.1 points higher (20.4 vs 12.3) but costs 2.1× as much to run the benchmark ($451 vs $218; both mid-range class). Pick DeepSeek V4 Pro 0813 (Non-reasoning) when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 12.3 | −39.7% Mercury 2.5 is 39.7% less intelligent |
| Total AA cost (lower is better) | $450.76 | $218.11 | −51.6% Mercury 2.5 is 51.6% cheaper |
| End-to-end time (lower is better) | 6.74s | 4.18s | −38.0% Mercury 2.5 is 38.0% faster |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.25 / $0.75 | |
| Input modalities | Text | Text |
Mercury 2.5 vs DeepSeek V4 Pro 0813 (Non-reasoning): 39.7% less intelligence, 51.6% less cost to run the AA benchmark, and 38.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Non-reasoning) 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 Pro 0813 (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-pro-non-reasoning/mercury-2-5 · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/mercury-2-5?format=md · llms.txt · agent skill