DE
CompareDeepSeek V3 0324
deepseek/deepseek-chat-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](/deepseek/deepseek-chat-v3) model and performs really well...
- Context window
- 164K
- Input
- Text
- Output
- Text
- Released
- 2025-03-24
- Max output
- 66K
- Knowledge cutoff
- 2024-07-31
- Model parameters
- 685B
- Weights
- Open
- Capabilities
- Open weight, Structured, Temperature, Tool call
No official pricing available.
Performance
Overall capability
40.3/100
- Coding
- 38.5
- Reasoning
- 35.6
- Professional work
- 28.2
- Knowledge & language
- 37.9
| AutomationBench-AADeepSeek V3 0324 | Professional work | Artificial Analysis | 2026-11-05 | |
| AA-Briefcase | Professional work | Artificial Analysis | 2026-11-05 | |
| GDPval-AA | Professional work | Artificial Analysis | 2026-11-05 | |
| IFBench（Artificial Analysis）DeepSeek V3 0324 | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| CritPtDeepSeek V3 0324 | Reasoning | Artificial Analysis | 2026-11-05 | |
| Humanity’s Last ExamDeepSeek V3 0324 | Reasoning | Artificial Analysis | 2026-11-05 | |
| Terminal-Bench 4.0 (AA rerun)DeepSeek V3 0324 | Coding | Artificial Analysis | 2026-11-05 | |
| AA-LCRDeepSeek V3 0324 | Knowledge & language | Artificial Analysis | 2026-11-05 |
Providers
No providers found
ModelRegistry · Catalog updated 2026-11-05