The Model Index
Up to four models

DeepSeek-V4-Flash vs DeepSeek-V4.1-Flash

On the index (GPT-4 = 100), DeepSeek-V4-Flash scores 164 and DeepSeek-V4.1-Flash 163. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to DeepSeek-V4-Flash
Presets
DeepSeek-V4-Flash
164133–195
WeightsOpen
ReleasedJul 2026
Price in / out–
Context–
Core tests taken0 of 9
DeepSeek-V4.1-Flash
163147–179
WeightsOpen
ReleasedSep 2026
Price in / out$0.051 / $0.57
Context1.05M
Core tests taken6 of 9

DeepSeek-V4-Flash and DeepSeek-V4.1-Flash are too close to call (1 point apart, within the uncertainty).

Test by testthird-party results

DeepSeek-V4-FlashDeepSeek-V4.1-Flash
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningMATHSLiveBench MathematicsLiveBench MathematicsCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench Coding
Every result as a table
TestDeepSeek-V4-FlashDeepSeek-V4.1-Flash
Reasoning & knowledge
LiveBench Data Analysis79.5%79.3%
LiveBench IF71.0%70.0%
LiveBench Language80.4%81.2%
LiveBench Reasoning85.4%86.7%
Maths
LiveBench Mathematics87.8%93.3%
Coding
LiveBench Agentic Coding65.1%77.3%
LiveBench Coding68.2%80.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG