DeepSeek-V3.1

Training compute

3.6×10²⁴ FLOP

Parameters

671B

Published

Aug 21, 2025

DeepSeek-V3.1 is an AI model developed by DeepSeek (China), first published in August 2025. It works in the language domain, on tasks such as language modeling/generation, code generation, quantitative reasoning and 4 more.

Training it took an estimated 3.6×10²⁴ FLOP of compute (estimation method: operation counting). The model has 671,000,000,000 parameters. It was trained on roughly 840B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of DeepSeek-V3. Epoch AI rates the confidence of this record as confident.

Full record

Organization: DeepSeek
Country of organization: China
Domain: Language
Task: Language modeling/generation, Code generation, Quantitative reasoning, Question answering, Search, System control, Instruction interpretation
Training compute: 3.6×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 671,000,000,000
Dataset size: 840B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: DeepSeek-V3
Epoch confidence: Confident

Benchmark results

01	ForecastBench	Overall score	58
02	Fictionlivebench	120k token score	0.53
03	SimpleBench	Score (AVG@5)	0.4
04	WeirdML	Accuracy	0.38