AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#248

DeepSeek V4.1 Flash

DeepSeek Release: 2026-09-10 Tested on: 2026-09-10 12:40 deepseek/deepseek-v4.1-flash::none
748B total (16B active)MoEOpen source
(max) (high) (medium) (low) (none)

Summary

DeepSeek V4.1 Flash scores 5.4 on AI BENCHY and ranks #248. It has 9.6 reliability, a 34.9% pass rate, $0.185 total cost, and 14.85s average response time.

What makes DeepSeek V4.1 Flash unique: It stands out most in Coding, where it ranks #1, while Data parsing and extraction is its weakest area at #12.

Model facts

Researched on 2026-09-10

Reported
Parameters
748B total (16B active)
Architecture
MoE
Availability
Open source
License
MIT

Total is 552B backbone plus 196B Engram conditional-memory parameters. Active count is 16B during decode; prefill activates 8B per token. The exact checkpoint includes MIT-licensed weights and a runnable inference implementation.

Parameter source Availability source

Score

5.4

Consistency

9.3

Reliability

9.6

Total Cost (Current Price)

$0.185

Total Output Tokens

273,780

Total Input Tokens

137,687

Input Price

$0.150 / 1M

Output Price

$0.600 / 1M

Tests Correct

Wrong Tests: 15

Attempt pass rate: 34.9%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

14.85s

Response Time (max): 247.66s

Response Time (total): 326.72s

Wrong answer: 11 Did not follow instructions: 2 API error: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#248 DeepSeek V4.1 Flash

none
Cost
$0.021
Time
55.4s
Tokens
17,181 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

DeepSeek V4.1 FlashnonevsDeepSeek V4 Flash 0423noneDeepSeek V4.1 FlashnonevsLaguna S 2.1mediumFree AvailableDeepSeek V4.1 FlashnonevsQwen3.8 27BnoneDeepSeek V4.1 FlashnonevsKAT-Coder-Air V2.5lowDeepSeek V4.1 FlashnonevsQwen3.6 27BnoneDeepSeek V4.1 FlashnonevsGPT-5.6 LunanoneDeepSeek V4.1 FlashnonevsHy4 previewlowDeepSeek V4.1 FlashnonevsMiMo-V2.5-PrononeDeepSeek V4.1 FlashnonevsNemotron 3.5 LightninghighFree AvailableDeepSeek V4.1 FlashnonevsKimi K2.5none

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.7 8.4
Coding 5.5 10.0
Combined 3.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 7.7 10.0
General Intelligence 5.5 10.0
Instructions following 6.5 10.0
Puzzle Solving 5.3 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models