DeepSeek R1 (Jan '25) vs GPT-5 mini (High)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick GPT-5 mini (High)
GPT-5 mini (High) vs DeepSeek R1 (Jan '25): 47.4% more intelligence, 59.1% less cost to run the AA benchmark, and 202.1% slower end-to-end.
| Metric | DeepSeek R1 (Jan '25) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 16.8 | +47.4% GPT-5 mini (High) is 47.4% more intelligent |
| Total AA cost (lower is better) | $460.74 | $188.66 | −59.1% GPT-5 mini (High) is 59.1% cheaper |
| End-to-end time (lower is better) | 20.16s | 60.90s | +202.1% GPT-5 mini (High) is 202.1% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.25 / $2.00 | |
| Input modalities | Text | Text, Image |
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.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
DeepSeek R1 (Jan '25)GPT-5 mini (High)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/gpt-5-mini · Markdown: /api/v1/compare/deepseek-r1-0120/gpt-5-mini?format=md · llms.txt · agent skill