Intelligence Index
0114.2
> 28% OF MODELS
DeepSeek
DeepSeek V3
Updated: August 2026
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Specifications
- Context
- 164K
- Input
- $0.2574/M
- Output
- $1.0287/M
Capabilities
TEXTWEBCODINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Minimax M2 | Minimax | 197K | $0.255/M | $1/M |
| Minimax M2 | Minimax | 197K | $0.255/M | $1/M |
| Qwen3.5-122B-A10B | Qwen | 262K | $0.26/M | $2.08/M |
| Qwen Plus 0728 | Qwen | 1M | $0.26/M | $0.78/M |
| Qwen-Plus | Qwen | 1M | $0.26/M | $0.78/M |
Performance Metrics
Coding Index
0223.0
> 30% OF MODELS
Agentic Index
031.6
> 11% OF MODELS
DATA SOURCE: Artificial Analysis