DeepSeek R1 (Jan '25) vs Mercury 2
Which is better for the money: DeepSeek R1 (Jan '25) 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 R1 (Jan '25) scores 0.6 points higher (11.4 vs 10.8) but costs 4.4× as much to run the benchmark ($461 vs $105; both mid-range class). They are not alternatives at one budget: pick DeepSeek R1 (Jan '25) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | DeepSeek R1 (Jan '25) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 10.8 | −5.3% Mercury 2 is 5.3% less intelligent |
| Total AA cost (lower is better) | $460.74 | $104.94 | −77.2% Mercury 2 is 77.2% cheaper |
| End-to-end time (lower is better) | 20.14s | 6.58s | −67.3% Mercury 2 is 67.3% faster |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.25 / $0.75 | |
| Input modalities | Text | Text |
Mercury 2 vs DeepSeek R1 (Jan '25): 5.3% less intelligence, 77.2% less cost to run the AA benchmark, and 67.3% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) 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 R1 (Jan '25)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-r1-0120/mercury-2 · Markdown: /api/v1/compare/deepseek-r1-0120/mercury-2?format=md · llms.txt · agent skill