Skip to content
llmwaves

V4 Flash 0423

DeepSeek · released Apr 24, 2026

Open weightsReasoningTool useStructured output

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Specification

Context window
1.05M
Max output
131K
Knowledge cutoff
Not stated
Parameters
290.9B
Licence
mit
Serving providers
20
Moderated
No
Uptime
100.0%

Intelligence

51.8

96th percentile

Coding

69.1

Coding Index

Agentic

48.4

Agentic Index

Output speed

87 t/s

Median across providers

Latency

371ms

Time to first token

Cost per task

$0.02

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    90.8%
  • AA-LCR (long context)
    74.3%
  • SciCode
    49.9%
  • τ²-bench (Telecom)
    39.4%
  • Humanity's Last Exam
    38.6%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond90.8%
AA-LCR (long context)74.3%
SciCode49.9%
τ²-bench (Telecom)39.4%
Humanity's Last Exam38.6%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Muse Spark 1.153.2
GPT-5.453.1
GLM 5.252.6
GPT-5.6 Luna52.3
Gemini 3.5 Flash52.0
V4 Flash 042351.8
V4 Flash 073151.8
Gemini 3.6 Flash51.6

Percentile among all indexed models

Intelligence96th
Coding86th
Agentic86th
Arena Elo68th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.088
Output / 1M tokens
$0.176
Cached input / 1M
$0.018
Blended 3:1
$0.11

One task, estimated

$0.02

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,244
Win rate
49.3%
Strongest at
3D scenes
Tournaments
8,019

Elo by category

Dot position on a 1,150–1,250 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
3D scenes124449.3%
Game development123850.2%
Websites123049.0%
SVG120048.4%
UI components119944.7%
Data visualisation115240.5%