D
DeepSeek Coder V2 Lite Instruct
Last updated: Recently
Model Type
Code
Max Context
-
Max Output
-
Parameter Scale
-
DeepSeek Coder V2 Lite Instruct by DeepSeek: Code model.
Input Modality
-
Output Modality
-
Inference Speed
-
Latest Release Date
6/17/2024
SDK Ecosystem
-
artificial-analysismanufactureraa-bootstrap
Model Overview Fields
name
DeepSeek Coder V2 Lite Instruct
Release date
6/17/2024
Performance
-
model_creator.name
DeepSeek
AA Evaluation Scores
AA Intelligence Index
8.5
AA Coding Index
-
AA Math Index
-
MMLU Pro
0.429
GPQA
0.319
HLE
0.053
LiveCodeBench
0.158
SciCode
0.139
Math-500
-
AIME
-
AIME 2025
-
IFBench
-
LCR
-
TerminalBench Hard
-
TAU2
-
Output Speed (tokens/s)
-
TTFT (s)
-
First Answer Token (s)
-

