DeepSeek V3 (2025-03-24)

deepseek/deepseek-chat-v3-0324

DeepSeek V3 (2025-03-24)

via OpenRouter

Release Date

Mar 24th, 2025

Context Size

163.8k

Reasoning

Benchmark Cost

$0.66

Speed

34.1 tok/s

Subcategories

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
Fantasy: entering an ancient ruin Creative Writing Hallucination	85	77	76	76	75	78%
Horror: alone in an eerie place at night Creative Writing Hallucination	90	87	83	81	74	83%
Literary fiction: old friends reunite Creative Writing Hallucination	87	87	85	85	80	85%
Mystery: examining a crime scene Creative Writing Hallucination	89	89	81	77	77	82%
Romance: separated couple reunites Creative Writing Hallucination	85	83	81	81	80	82%
Thriller: chase through city streets Creative Writing Hallucination	88	86	85	82	79	84%
Detailed Writing Rules						82.38%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	81	77	74	72	72	75%
Horror: alone in an eerie place at night Creative Writing Hallucination	90	87	85	82	82	85%
Literary fiction: old friends reunite Creative Writing Hallucination	91	87	86	80	78	85%
Mystery: examining a crime scene Creative Writing Hallucination	83	83	80	80	72	80%
Romance: separated couple reunites Creative Writing Hallucination	87	86	84	84	82	85%
Thriller: chase through city streets Creative Writing Hallucination	94	81	80	76	73	81%
genre						81.66%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	80	80	79	74	73	77%
Horror: alone in an eerie place at night Creative Writing Hallucination	84	83	83	80	75	81%
Literary fiction: old friends reunite Creative Writing Hallucination	84	83	81	81	77	81%
Mystery: examining a crime scene Creative Writing Hallucination	87	83	83	80	75	82%
Romance: separated couple reunites Creative Writing Hallucination	86	84	84	82	82	84%
Thriller: chase through city streets Creative Writing Hallucination	82	81	81	76	76	79%
Novelcrafter Default Prompt						80.57%
81.53%

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
Long: The Spire of Echoes (Dense) Tooling Reasoning	96	95	93	92	92	94%
Medium: The Hollow (Inferred) Tooling Reasoning	96	94	93	92	91	94%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	96	96	95	95	95	95%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	100	99	99	99	96	98%
95.18%

Codex Red Herring (False Positive Detection)

Tests whether models correctly report "no violations" when a codex is fully consistent with the prose passage. Models that hallucinate false violations (false positives) fail. Uses a 2×2 matrix of text length × codex size, with bare and detailed-entry variants.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
basic entries
Long text (~1594 words), big codex (51 entries) Hallucination	13	13	10	10	8	7	7	6	6	4	8%
Long text (~1594 words), small codex (11 entries) Hallucination	42	35	33	10	10	10	10	10	8	7	18%
Short text (~524 words), big codex (51 entries) Hallucination	25	25	17	13	13	13	13	10	7	7	14%
Short text (~524 words), small codex (11 entries) Hallucination	25	25	25	25	25	25	25	17	17	17	23%
basic entries											15.64%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	8	8	6	5	5	5	5	5	1	1	5%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	25	17	13	13	13	13	13	10	8	8	13%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	25	25	25	25	17	17	13	8	35%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	25	25	25	25	25	25	25	25	25	33%
detailed entries											21.46%
18.55%

Codex Violation Detection

Detects factual inconsistencies between a story bible and prose passages. The model must output structured XML identifying each violation with paragraph number and substring.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
matrix
Large codex (40 entries), long passage (1,019 words) Tooling Reasoning	88	86	77	77	75	73	71	66	66	3	68%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	96	96	87	87	85	83	83	78	72	3	77%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	90	90	87	80	80	80	76	76	76	75	81%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	100	100	100	100	100	100	100	100	100	93	99%
matrix											81.46%
tiers
5 codex entries Tooling Reasoning	100	100	100	100	100	100	100	100	93	93	99%
10 codex entries Tooling Reasoning	100	100	100	94	94	94	92	86	86	86	93%
20 codex entries Tooling Reasoning	86	86	82	82	77	77	73	73	73	51	76%
40 codex entries Tooling Reasoning	93	92	88	87	83	79	75	75	74	71	82%
tiers											87.48%
84.47%

Data extraction

Extract key details from a given block of text.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
All valid emails Utility	100	100	100	100	100	100	100	100	100	100	100%
Contextual pronoun Utility	100	100	100	100	100	100	100	100	100	50	95%
Fruits excluding citrus Utility	100	100	100	100	100	100	100	100	100	100	100%
Future event time Reasoning	50	50	50	50	50	50	50	50	50	50	50%
Guess the pet Reasoning	100	100	100	100	100	100	100	100	100	50	95%
Highest-rated movie Reasoning	100	100	100	100	100	100	100	100	100	100	100%
Indirect birth year Reasoning	100	100	100	100	100	100	50	50	50	50	80%
What instrument does Lucy play? Reasoning	100	100	100	100	100	100	100	100	100	100	100%
What's the color of the car? Utility	100	100	100	100	100	100	100	100	100	100	100%
What's the correct time? Reasoning	100	100	100	100	100	100	100	0	0	0	70%
Who's the sister? Reasoning	100	100	100	100	100	100	100	100	100	100	100%
Who's the tallest? Reasoning	100	100	100	100	100	100	100	100	100	100	100%
90.83%

Dialogue tags

Various tasks related to dialogue tags in text.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
dialogue-200
Write 200 words with 10% dialogue Rule Following Utility	56	50	50	49	45	38	38	30	2	0	36%
Write 200 words with 50% dialogue Rule Following Utility	72	63	56	55	51	50	50	43	38	10	49%
Write 200 words with 90% dialogue Rule Following Utility	86	71	53	50	50	50	47	32	22	0	46%
dialogue-200											43.57%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	43	13	0	0	0	0	0	0	0	0	6%
Write 500 words with 50% dialogue Rule Following Utility	50	32	7	2	1	0	0	0	0	0	9%
Write 500 words with 70% dialogue Rule Following Utility	49	49	22	6	5	5	2	1	0	0	14%
dialogue-500											9.54%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	100	100%
37.05%

Language Comprehension

Does the model understand more than just English?

Scenario	#1	#2	#3	#4	#5	Total
Asking for directions (Dutch) Language	100	100	100	100	100	100%
Asking for directions (German) Language	100	100	100	100	100	100%
Friend got new kittens (German) Language	100	100	100	100	100	100%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
100.00%

Language Writing

Can the model generate text in different languages?

Scenario	#1	#2	#3	#4	#5	Total
Character dialogue (French) in a story Language	100	100	100	100	100	100%
Character dialogue (German) in a story Language	100	100	100	100	89	98%
Character dialogue (Hindi) in a story Language	100	100	56	0	0	51%
Character dialogue (Italian) in a story Language	100	100	89	0	0	58%
Character dialogue (Spanish) in a story Language	100	100	88	0	0	57%
72.83%

N-Length Sentences

Write sentences with exactly N words

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
Write sentences with 5 words each Utility	100	100	100	100	100	98	98	98	88	81	96%
Write sentences with 10 words each Utility	97	97	92	92	84	74	74	74	72	72	83%
Write sentences with 20 words each Utility	74	58	51	39	27	24	18	11	8	0	31%
70.17%

Novel outline

Handle questions about the outline of a novel in various formats

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
outline-count
Count acts Utility	100	100	100	100	100	100	100	100	100	0	90%
Count chapters Utility	100	100	100	100	100	100	100	100	100	0	90%
Count scenes Utility	100	100	100	100	100	100	100	100	100	0	90%
outline-count											90.00%
pov-count
Count point of views for Jack and Olivia Utility	100	50	50	50	0	0	0	0	0	0	25%
Count point of views for Jack Harper Utility	100	100	100	100	100	0	0	0	0	0	50%
Count point of views for Olivia Utility	100	100	100	100	100	100	100	100	100	0	90%
pov-count											55.00%
72.50%

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
Avoid said/asked/replied/answered Text Editing	100	100	100	100	100	100	100	100%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	100	100	100	85	98%
Combined: 3rd person past → 1st person present Text Editing	98	98	97	97	97	97	96	97%
Expand all contractions Text Editing	100	100	100	100	100	100	99	100%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	100	95	93	58	92%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	91	74	74	74	70	83%
Passive voice → active voice Text Editing Hallucination	95	93	93	92	86	78	77	88%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	97	96	96	66	94%
Tense rewriting: past to present Text Editing	96	96	96	95	95	89	20	84%
Generic Prompt								92.87%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	100	100	100	100	100	100	100	100%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	100	100	100	54	93%
Combined: 3rd person past → 1st person present Text Editing	99	99	99	99	99	99	0	85%
Expand all contractions Text Editing	100	100	100	100	100	99	98	100%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	100	100	100	100	100%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	100	100	100	100	95	99%
Passive voice → active voice Text Editing Hallucination	97	97	96	95	94	70	20	81%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	46	0	78%
Tense rewriting: past to present Text Editing	100	100	100	100	100	100	100	100%
Specific Prompt								92.97%
92.92%

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
Create alternate prose sections Tooling	100	100	100	100	100	100	100	100	100	0	90%
90.00%

Voice/dialogue sheets

Extract dialogue from given text as voice sheets.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
Multiple speakers Rule Following	100	100	100	100	100	0	0	0	0	0	50%
Simple Rule Following	100	100	100	100	100	100	100	100	100	0	90%
Simple (1-shot) 1-shot Rule Following	100	100	100	100	100	100	100	100	100	100	100%
Simple (5-shot) Few-shot Rule Following	100	100	100	100	100	100	100	100	100	100	100%
Unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	0	0	80%
84.00%

Write N of X

Write exactly N words/sentences/paragraphs...

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
paragraphs
1 paragraph summary Utility	100	100	100	100	100	100	100	100	100	100	100%
3 paragraph summary Utility	100	100	100	100	100	100	100	100	0	0	80%
5 paragraph summary Utility	100	100	100	100	100	100	100	100	100	100	100%
paragraphs											93.33%
sentences
1 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
3 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
10 sentence summary Utility	100	100	100	100	100	100	100	100	100	98	100%
20 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
50 sentence summary Utility	100	100	100	100	100	100	100	100	100	0	90%
sentences											97.96%
words
10 word summary Utility	100	100	100	100	100	100	100	100	98	92	99%
20 word summary Utility	100	100	100	100	100	100	100	100	100	98	100%
50 word summary Utility	100	98	98	92	92	77	54	54	2	0	67%
100 word summary Utility	100	100	100	98	92	92	92	92	27	0	79%
200 word summary Utility	98	27	0	0	0	0	0	0	0	0	13%
words											71.50%
86.72%