DeepSeek V3 (Dec '24) vs GPT-5 mini (High)
Which is better for the money: DeepSeek V3 (Dec '24) 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.
Trade-off
Verdict
Depends on your budget
GPT-5 mini (High) scores 8.3 points higher (16.8 vs 8.5) but costs 7.4× as much to run the benchmark ($189 vs $25.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-5 mini (High) when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 16.8 | +97.6% GPT-5 mini (High) is 97.6% more intelligent |
| Total AA cost (lower is better) | $25.37 | $188.66 | +643.6% GPT-5 mini (High) is 7.4× more expensive |
| End-to-end time (lower is better) | 11.84s | 58.72s | +395.9% GPT-5 mini (High) is 395.9% slower |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.25 / $2.00 | |
| Input modalities | Text | Text, Image |
GPT-5 mini (High) vs DeepSeek V3 (Dec '24): 97.6% more intelligence, 643.6% more cost to run the AA benchmark, and 395.9% slower 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.
- 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 V3 (Dec '24)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-v3/gpt-5-mini · Markdown: /api/v1/compare/deepseek-v3/gpt-5-mini?format=md · llms.txt · agent skill