#27
DeepSeek V4.1 Flash
deepseek-v4.1-flash
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 94 tok/s
Release Date
September 10th, 2026
Lab
DeepSeek
Type
Open Source
Context Size
1M
Max Output Tokens
384K
Cost per 1 million tokens
$0.15 / $0.60
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
89.50 pts
Rank #27
69th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
DeepSeek V4.1 Flash is DeepSeek's September 2026 open assistant: native vision, a 1M context, and cheaper, faster inference than V4 Pro—which it now outperforms on our tests for most everyday help. Helpfulness, instruction following, and comprehension are strong for the price. Empathy stays thin, and creative writing is readable but formulaic. The default open model when you want lots of good-enough help without paying frontier rates.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
DeepSeek
Google
Meta
Moonshot
OpenAI
SpaceX AI
Zhipu AI

Intelligence

Overall Score · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M input tokens · Lower is better

DeepSeek Models

Overall Score · Same provider

DeepSeek Family

Overall Score · Same model family

Closest Rivals

Overall Score · Nearest by overall rank