DeepSeek R1 (Jan '25) vs DeepSeek V4 Flash 0731 (Max)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or DeepSeek V4 Flash 0731 (Max) by DeepSeek? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick DeepSeek V4 Flash 0731 (Max)
DeepSeek V4 Flash 0731 (Max) vs DeepSeek R1 (Jan '25): 200.9% more intelligence, 56.7% less cost to run the AA benchmark, and 11.0% faster end-to-end.
| Metric | DeepSeek R1 (Jan '25) | DeepSeek V4 Flash 0731 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 34.3 | +200.9% DeepSeek V4 Flash 073… is 3.0× more intelligent |
| Total AA cost (lower is better) | $460.74 | $199.63 | −56.7% DeepSeek V4 Flash 073… is 56.7% cheaper |
| End-to-end time (lower is better) | 20.16s | 17.94s | −11.0% DeepSeek V4 Flash 073… is 11.0% faster |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.14 / $0.28 | |
| Input modalities | Text | Text |
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.
- DeepSeek V4 Flash 0731 (Max) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
DeepSeek R1 (Jan '25)DeepSeek V4 Flash 0731 (Max)Today'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/deepseek-v4-flash · Markdown: /api/v1/compare/deepseek-r1-0120/deepseek-v4-flash?format=md · llms.txt · agent skill