DeepSeek: DeepSeek V3 0324
Analysis Summary
DeepSeek V3 0324 is a capable general-purpose model with a coding index of 21.2 and agentic index of 31.1, supported by tool use and function calling. Its GPQA of 0.655 and MMLU-Pro of 0.819 show strong knowledge breadth, and the 163K context window handles long documents comfortably. The intelligence index of 15.4 reflects a mid-tier position relative to the current landscape.
For businesses, it suits coding assistance, structured data extraction, and tool-augmented workflows where cost efficiency is a priority. The livecodebench score of 0.405 and tau2 of 0.47 indicate reliable agentic task completion. It does not reach frontier reasoning quality, so high-stakes analytical work may benefit from a more capable model.
At $0.20 input and $0.77 output per million tokens, it is priced aggressively for its capability level. Teams running moderate-complexity coding pipelines or tool-use workflows at scale will find strong value here, though a -4 point regional penalty applies given provider accessibility considerations for enterprise deployments.
Assessed June 30, 2026
Editorial notes
DeepSeek V3 0324 delivers strong coding and agentic scores with tool use and function calling at very competitive pricing, though its intelligence index of 15.4 sits below the current frontier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How DeepSeek: DeepSeek V3 0324 compares
DeepSeek: DeepSeek V3 0324 ranks #172 of 385 AI models we track for overall intelligence, #84 of 139 for coding, #143 of 293 for agentic tasks. Its 164K-token context window is larger than 61% of the models we list. At $0.24 per million input tokens it is cheaper than 48% of comparable models.
About DeepSeek: DeepSeek V3 0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does DeepSeek: DeepSeek V3 0324 stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.24 | $0.000240 |
| Output | $0.90 | $0.000900 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about DeepSeek: DeepSeek V3 0324
How much does DeepSeek: DeepSeek V3 0324 cost?
DeepSeek: DeepSeek V3 0324 costs $0.24 per million input tokens and $0.90 per million output tokens.
What is the context window of DeepSeek: DeepSeek V3 0324?
DeepSeek: DeepSeek V3 0324 has a context window of 163,840 tokens (164K).
Is DeepSeek: DeepSeek V3 0324 good for coding?
On our coding benchmark index, DeepSeek: DeepSeek V3 0324 ranks #84 of 139 models, placing it in the broader range of the field for code generation and debugging.
What can DeepSeek: DeepSeek V3 0324 do?
DeepSeek: DeepSeek V3 0324 supports tool use and function calling.
Who created DeepSeek: DeepSeek V3 0324?
DeepSeek: DeepSeek V3 0324 is developed by DeepSeek and was released on March 24, 2025.
