MMODELYST
Models/DeepSeek-Coder-V2
MDL

DeepSeek-Coder-V2

DeepSeek

Verified against Artificial Analysis · Jul 13, 2026
Capability
percentile index
Price /M
$0 / $0
in / out
Context
Avg score
74.3
1 benchmarks
AA Intelligence
5.1
index
Weights
Open
Released
Jun 17, 2024
About

DeepSeek-Coder-V2 is a open-weights model in the DeepSeek family from DeepSeek. Benchmarked on 1 eval, averaging 74.3.

Benchmark scores · 1
avg 74.3 — higher is better
MATH
74.3
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherDeepSeek
FamilyDeepSeek
Parameters
License
WeightsOpen
ReleasedJun 17, 2024
API providers
Artificial Analysis$0/M