AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#51

DeepSeek V4.1 Flash

DeepSeek Release: 2026-09-10 Tested on: 2026-09-10 12:39 deepseek/deepseek-v4.1-flash::low
748B total (16B active)MoEOpen source
(max) (high) (medium) (low) (none)

Summary

DeepSeek V4.1 Flash scores 8.5 on AI BENCHY and ranks #51. It has 9.5 reliability, a 74.2% pass rate, $0.224 total cost, and 26.77s average response time.

What makes DeepSeek V4.1 Flash unique: Its total benchmark cost is unusually low for its score range.

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

8.5

Consistency

8.9

Reliability

9.5

Total Cost (Current Price)

$0.224

Total Output Tokens

347,963

Total Input Tokens

99,715

Input Price

$0.150 / 1M

Output Price

$0.600 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 74.2%

Flaky tests

3

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

Response Time (avg)

26.77s

Response Time (max): 149.84s

Response Time (total): 589.01s

Wrong answer: 6 API error: 1

Hamster playing table tennis

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

#51 DeepSeek V4.1 Flash

low
Cost
$0.017
Time
43.6s
Tokens
14,069 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 FlashlowvsGPT-5.4mediumDeepSeek V4.1 FlashlowvsDeepSeek V4.1 FlashhighDeepSeek V4.1 FlashlowvsQwen3.8 MaxlowDeepSeek V4.1 FlashlowvsDeepSeek V4.1 FlashmediumDeepSeek V4.1 FlashlowvsQwen3.6 Max PreviewmediumDeepSeek V4.1 FlashlowvsGrok 4.5mediumDeepSeek V4.1 FlashlowvsClaude Fable 5mediumDeepSeek V4.1 FlashlowvsMuse Spark 1.2lowDeepSeek V4.1 FlashlowvsMuse Spark 1.1mediumDeepSeek V4.1 FlashlowvsGrok 4.6medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 3.5 4.4
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 8.2 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models