deepseek/deepseek-v3.2

DeepSeek V3.2

Release Date

Dec 1st, 2025

Context Size

163.8k

Reasoning

Yes

Benchmark Cost

$0.63

Speed

24.8 tok/s

Categories

20%40%60%80%100%Creative Writing79.9%Tooling100.0%Language85.0%Utility81.6%Reasoning89.5%Text Editing95.8%Rule Following53.8%Hallucination72.5%

Subcategories

20%40%60%80%100%AI-ismsProse VarietyDialoguePurple ProseMechanical StyleClichésXMLComprehensionGenerationWord CountingSentence CountingParagraph CountingStructural CountingData ExtractionDeductionAttentionTransformationPreservationStructural IntegrityConstraint AdherenceFalse PositivesContent InventionOutput Corruption

Bad Writing Habits

Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.

Scenario #1 #2 #3 #4 #5 Total
Detailed Writing Rules
857979797679%
878582817983%
868582827782%
858281807982%
888582807983%
848482828083%
Detailed Writing Rules81.89%
genre
787671717173%
838079787880%
828274737076%
847875727076%
838080747278%
818079757478%
genre76.72%
Novelcrafter Default Prompt
797473706973%
837978777578%
818080797679%
868178767679%
848381817681%
868280787480%
Novelcrafter Default Prompt78.45%
79.02%

Codex Extraction

Evaluates a model's ability to extract structured codex entries (characters, locations, objects, lore) from prose passages and return them as well-formed XML.

Scenario #1 #2 #3 #4 #5 Total
979696959596%
989795959496%
979796959396%
1009998978596%
95.69%

Text Replacement

Tests deterministic text transformations: renaming characters/locations, expanding contractions, tense rewriting, POV shifts, gender swaps, combined transformations, and word avoidance. Scored by checking each expected change independently.

Scenario #1 #2 #3 #4 #5 #6 #7 Total
Generic Prompt
100100100100100100100100%
100100100100100100100100%
9999999999999999%
10010010010010010099100%
100100100100100100100100%
7474747474747474%
9797969696959496%
100100100100100100100100%
9696938988878591%
Generic Prompt95.41%
Specific Prompt
100100100100100100100100%
100100100100100100100100%
9999999999999999%
100100100100100100100100%
100100100100100100100100%
100100100100100100100100%
9999999998989799%
100100100100100100100100%
100100100100100100100100%
Specific Prompt99.77%
97.59%

Tool usage within Novelcrafter

Output messages that are related to tool usage within Novelcrafter

Scenario #1 #2 #3 #4 #5 #6 #7 #8 #9 #10 Total
100100100100100100100100100100100%
100.00%