DeepSeek V3 (Dec '24)
By DeepSeek · released 2024-12-26 (19 months) · snapshot 2026-08-07
- Intelligence index
- 14.20
- Cost to run the AA index
- $20.0
- Price per 1M tokens (in / out)
- $0.36 / $0.89
Is DeepSeek V3 (Dec '24) on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-5.6 Luna (low) is at least as smart for the same money or less.
Next step up: GPT-5.6 Luna (medium), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V3 (Dec '24) | DeepSeek | 14.20 | $20.0 | - | 2024-12-26 | ||
| 2 | GPT-5.6 Luna (low) | OpenAI | 33.90 | $13.7 | 5.53s | 2026-07-09 | Frontier | |
| 3 | GPT-5.6 Luna (medium) | OpenAI | 38.90 | $21.1 | 5.72s | 2026-07-09 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
DeepSeek V3 (Dec '24) today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: deepseek-v3.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
What the DeepSeek V3 release did to the frontier on 2024-12-26
1 of 1 effort levels reached the frontier at launch (DeepSeek V3 (Dec '24)). Impact 0, did not move the frontier; 41 releases this past year did.
Should you use DeepSeek V3 (Dec '24)?
Should you use DeepSeek V3 (Dec '24)?
Only when it fits your setup: GPT-5.6 Luna (low) is at least as smart for the same money or less, so DeepSeek V3 (Dec '24) is off the value frontier today.
What is better and cheaper than DeepSeek V3 (Dec '24)?
GPT-5.6 Luna (low) — at least as smart for the same money or less.
How much does DeepSeek V3 (Dec '24) cost?
$0.36/$0.89 in/out per 1M tokens, and $20.0 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is DeepSeek V3 (Dec '24) on the Pareto frontier?
No: GPT-5.6 Luna (low) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where DeepSeek V3 (Dec '24) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | no data |
| AA intelligence index | Output speed tokens/sec | no data |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/deepseek-v3 · Markdown: /api/v1/models/deepseek-v3?format=md · llms.txt · agent skill