DeepSeek V3 (Dec '24) vs Mercury 2.5
Which is better for the money: DeepSeek V3 (Dec '24) 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
Mercury 2.5 scores 3.8 points higher (12.3 vs 8.5) but costs 8.6× as much to run the benchmark ($218 vs $25.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick Mercury 2.5 when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 12.3 | +44.7% Mercury 2.5 is 44.7% more intelligent |
| Total AA cost (lower is better) | $25.37 | $218.11 | +759.7% Mercury 2.5 is 8.6× more expensive |
| End-to-end time (lower is better) | 11.84s | 4.32s | −63.5% Mercury 2.5 is 63.5% faster |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.25 / $0.75 | |
| Input modalities | Text | Text |
Mercury 2.5 vs DeepSeek V3 (Dec '24): 44.7% more intelligence, 759.7% more cost to run the AA benchmark, and 63.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek V3 (Dec '24)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-v3/mercury-2-5 · Markdown: /api/v1/compare/deepseek-v3/mercury-2-5?format=md · llms.txt · agent skill