Skip to main content

DeepSeek V3 vs DeepSeek V4 Flash

SpecDeepSeek V3DeepSeek V4 Flash
Respan Index13.2 (#166)45.4 (#54)
Blended price per 1M$0.175$0.113
Context window128K1M
Input / output per 1M$0.14 / $0.28$0.09 / $0.18
Max output8K-
Inputtexttext
Released2024-12-262026-07-31

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryDeepSeek V3DeepSeek V4 Flash
Coding3.1 DeepSeek V329.7 DeepSeek V4 Flash
Agents5.6* DeepSeek V358.0 DeepSeek V4 Flash
Reasoning17.3 DeepSeek V346.1 DeepSeek V4 Flash
Knowledge & language7.8 DeepSeek V335.5 DeepSeek V4 Flash
Human preference39.4 DeepSeek V355.9 DeepSeek V4 Flash

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

DeepSeek V4 Flash leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V3DeepSeek V4 Flash
LMArena Elo13581436
GPQA Diamond59.1%91%
OTIS Mock AIME 2024-2025 (Epoch AI)15.8%94.4%
SimpleBench (SimpleBench)18.9%61.1%
WeirdML (Håvard Tveit Ihle)36.1%63%

FAQ

Is DeepSeek V3 better than DeepSeek V4 Flash?

DeepSeek V4 Flash scores 45.4 on the Respan Index (#54), ahead of DeepSeek V3 at 13.2 (#166). DeepSeek V4 Flash leads on 5 of the 5 benchmarks both report.

Which is cheaper, DeepSeek V3 or DeepSeek V4 Flash?

DeepSeek V3 lists at $0.14 input and $0.28 output per 1M tokens; DeepSeek V4 Flash at $0.09 and $0.18. DeepSeek V4 Flash is 1.6x cheaper per token at list price.

Which has the larger context window?

DeepSeek V3 accepts 128K tokens and DeepSeek V4 Flash 1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.