DeepSeek-Coder-V2-Instruct

Name: DeepSeek-Coder-V2-Instruct
Rating: 23.5 (700 reviews)
Author: DeepSeek

#2508Large Language ModelsProprietary

DeepSeek

DeepSeek-Coder-V2-Instruct is a proprietary DeepSeek llm model with a 16,384 token context window.

Model updates refreshed23m agoAug 25, 2026news + changelog

Website View Updates Start Free Trial

23.5

Quality Score

1193

Arena ELO

236B

Parameters

16K

Context

Evidence profile

How complete is this record?

This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.

64%

coverage

Developing evidence

14 of 22 public signals

Technical profile80%

Benchmarks and Competitive Signal

Arena only

Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.

This model has live arena signal, but it does not have structured benchmark rows or provider benchmark evidence yet.

A full normalized benchmark row is not available for this model yet.

Live arena evidence is already available below, so there is still a competitive signal even without a full benchmark table yet.

Arena ELO Ratings