DeepSeek V3 (2024-12-26)

deepseek/deepseek-chat

DeepSeek V3 (2024-12-26)

via OpenRouter

Release Date

Dec 26th, 2024

Context Size

163.8k

Reasoning

Benchmark Cost

$0.89

Speed

26.9 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	82	81	80	74	71	78%
Horror: alone in an eerie place at night Creative Writing Hallucination	87	79	79	73	73	78%
Literary fiction: old friends reunite Creative Writing Hallucination	87	85	80	78	76	81%
Mystery: examining a crime scene Creative Writing Hallucination	78	77	77	73	68	75%
Romance: separated couple reunites Creative Writing Hallucination	85	80	79	79	75	80%
Thriller: chase through city streets Creative Writing Hallucination	83	82	77	76	76	79%
Detailed Writing Rules						78.30%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	77	72	69	68	64	70%
Horror: alone in an eerie place at night Creative Writing Hallucination	86	75	73	72	69	75%
Literary fiction: old friends reunite Creative Writing Hallucination	82	82	79	76	72	78%
Mystery: examining a crime scene Creative Writing Hallucination	78	77	75	74	70	75%
Romance: separated couple reunites Creative Writing Hallucination	83	75	73	72	71	75%
Thriller: chase through city streets Creative Writing Hallucination	90	80	80	77	73	80%
genre						75.50%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	82	76	74	74	70	75%
Horror: alone in an eerie place at night Creative Writing Hallucination	88	79	79	77	70	78%
Literary fiction: old friends reunite Creative Writing Hallucination	82	78	78	73	71	76%
Mystery: examining a crime scene Creative Writing Hallucination	83	81	80	79	72	79%
Romance: separated couple reunites Creative Writing Hallucination	86	85	80	79	71	80%
Thriller: chase through city streets Creative Writing Hallucination	86	78	76	76	76	78%
Novelcrafter Default Prompt						77.97%
77.26%

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	94	93	92	92	93%
Medium: The Hollow (Inferred) Tooling Reasoning	95	94	91	90	88	92%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	97	96	95	94	89	94%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	98	97	97	95	94	96%
93.91%

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	30	25	25	17	13	13	10	5	4	2	14%
Long text (~1594 words), small codex (11 entries) Hallucination	31	25	17	13	13	13	13	13	13	8	16%
Short text (~524 words), big codex (51 entries) Hallucination	50	25	25	25	25	25	25	13	7	6	23%
Short text (~524 words), small codex (11 entries) Hallucination	100	28	25	25	25	25	25	25	25	17	32%
basic entries											21.09%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	25	17	10	7	6	6	5	5	4	3	9%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	33	25	25	25	17	13	13	8	8	8	18%
Short text (~524 words), big codex (51 detailed entries) Hallucination	25	25	25	25	25	17	17	13	10	8	19%
Short text (~524 words), small codex (11 detailed entries) Hallucination	25	25	25	25	25	25	25	25	25	25	25%
detailed entries											17.57%
19.33%

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	89	88	86	85	84	83	79	72	65	58	79%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	95	93	92	85	85	85	83	83	81	80	86%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	90	87	84	80	80	80	80	76	76	76	81%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	100	100	100	100	100	100	100	100	100	97	100%
matrix											86.42%
tiers
5 codex entries Tooling Reasoning	100	100	100	100	100	100	93	93	93	76	96%
10 codex entries Tooling Reasoning	94	92	89	86	86	86	79	79	72	72	84%
20 codex entries Tooling Reasoning	94	91	91	86	86	86	82	73	73	65	83%
40 codex entries Tooling Reasoning	97	92	92	84	84	83	80	79	76	75	84%
tiers											86.57%
86.49%

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	100	100%
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	100	100	100	100	100%
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	0	0	0	0	0	0	0	30%
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%
89.58%

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	74	50	50	47	17	14	14	3	0	0	27%
Write 200 words with 50% dialogue Rule Following Utility	70	68	64	56	51	50	41	41	37	0	48%
Write 200 words with 90% dialogue Rule Following Utility	100	100	88	70	50	48	26	25	6	0	51%
dialogue-200											41.98%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	50	49	47	22	0	0	0	0	0	0	17%
Write 500 words with 50% dialogue Rule Following Utility	49	47	41	18	14	5	2	0	0	0	17%
Write 500 words with 70% dialogue Rule Following Utility	85	51	36	28	19	16	15	14	3	2	27%
dialogue-500											20.37%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	100	100%
41.00%

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	94	0	79%
Character dialogue (German) in a story Language	100	100	100	100	0	80%
Character dialogue (Hindi) in a story Language	100	100	0	0	0	40%
Character dialogue (Italian) in a story Language	100	100	100	100	0	80%
Character dialogue (Spanish) in a story Language	100	100	100	100	100	100%
75.76%

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	100	96	93	86	70	95%
Write sentences with 10 words each Utility	92	90	89	87	87	82	77	70	65	59	80%
Write sentences with 20 words each Utility	49	44	35	21	21	19	18	10	2	0	22%
65.48%

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	100	100%
Count chapters Utility	100	100	100	100	100	100	100	100	100	100	100%
Count scenes Utility	100	100	100	100	0	0	0	0	0	0	40%
outline-count											80.00%
pov-count
Count point of views for Jack and Olivia Utility	100	100	100	100	100	50	0	0	0	0	55%
Count point of views for Jack Harper Utility	100	100	100	100	100	100	0	0	0	0	60%
Count point of views for Olivia Utility	100	100	100	100	100	0	0	0	0	0	50%
pov-count											55.00%
67.50%

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	100	100%
Combined: 3rd person past → 1st person present Text Editing	98	98	98	98	98	97	96	97%
Expand all contractions Text Editing	100	100	100	100	100	100	100	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	74	74	74	74	74	81%
Passive voice → active voice Text Editing Hallucination	95	94	93	93	93	91	90	93%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	100	99	100%
Tense rewriting: past to present Text Editing	96	95	95	95	88	81	81	90%
Generic Prompt								95.71%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	100	100	100	100	100	100	56	94%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	100	100	100	100	100%
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	100	100	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	100	100%
Passive voice → active voice Text Editing Hallucination	97	97	97	95	94	94	93	95%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	100	100	100%
Tense rewriting: past to present Text Editing	100	100	100	100	100	100	99	100%
Specific Prompt								97.11%
96.41%

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	100	100%
100.00%

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	100	100%
Simple (1-shot) 1-shot Rule Following	100	100	100	100	100	100	100	0	0	0	70%
Simple (5-shot) Few-shot Rule Following	100	100	100	100	100	100	100	100	100	0	90%
Unattributed dialogue Rule Following	100	100	100	100	100	100	0	0	0	0	60%
74.00%

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	100	100	100%
5 paragraph summary Utility	100	100	100	100	100	100	100	100	100	100	100%
paragraphs											100.00%
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	92	2	89%
20 sentence summary Utility	100	100	100	100	98	98	92	92	27	27	84%
50 sentence summary Utility	100	100	100	100	100	100	98	0	0	0	70%
sentences											88.56%
words
10 word summary Utility	100	100	100	100	98	98	98	98	92	92	98%
20 word summary Utility	100	100	100	100	100	100	100	100	98	92	99%
50 word summary Utility	100	100	98	92	92	54	27	27	9	0	60%
100 word summary Utility	100	100	100	98	92	92	77	54	54	0	77%
200 word summary Utility	100	100	77	0	0	0	0	0	0	0	28%
words											72.25%
84.93%