DeepSeek V3 (Dec '24) vs DeepSeek V3 0324
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or DeepSeek V3 0324 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 V3 0324
DeepSeek V3 0324 vs DeepSeek V3 (Dec '24): 14.1% more intelligence, 21.7% less cost to run the AA benchmark, and 59.0% faster end-to-end.
| Metric | DeepSeek V3 (Dec '24) | DeepSeek V3 0324 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 9.7 | +14.1% DeepSeek V3 0324 is 14.1% more intelligent |
| Total AA cost (lower is better) | $25.37 | $19.87 | −21.7% DeepSeek V3 0324 is 21.7% cheaper |
| End-to-end time (lower is better) | 11.84s | 4.86s | −59.0% DeepSeek V3 0324 is 59.0% faster |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.24 / $0.90 | |
| Input modalities | Text | Text |
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.
- DeepSeek V3 0324 is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
DeepSeek V3 (Dec '24)DeepSeek V3 0324Today'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/deepseek-v3-0324 · Markdown: /api/v1/compare/deepseek-v3/deepseek-v3-0324?format=md · llms.txt · agent skill