DeepSeek-V2.5

Training compute

1.8×10²⁴ FLOP

Parameters

236B

Published

Sep 6, 2024

DeepSeek-V2.5 is an AI model developed by DeepSeek (China), first published in September 2024. It works in the language domain, on tasks such as language modeling/generation, chat and code generation.

Training it took an estimated 1.8×10²⁴ FLOP of compute (estimation method: operation counting). The model has 236,000,000,000 parameters.

Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: DeepSeek
Country of organization: China
Domain: Language
Task: Language modeling/generation, Chat, Code generation
Training compute: 1.8×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 236,000,000,000
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident

Benchmark results

01

Aider Polyglot

Percent correct

17.8