Arcee AI: Trinity Mini

arcee-ai/trinity-mini

Arcee AI: Trinity Mini

via OpenRouter

Release Date

Dec 1st, 2025

Context Size

128k

Reasoning

Yes

Benchmark Cost

$0.25

Speed

182.2 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	72	71	68	65	59	67%
Horror: alone in an eerie place at night Creative Writing Hallucination	86	76	74	72	70	76%
Literary fiction: old friends reunite Creative Writing Hallucination	78	78	76	74	71	76%
Mystery: examining a crime scene Creative Writing Hallucination	81	76	74	71	66	74%
Romance: separated couple reunites Creative Writing Hallucination	81	76	75	75	72	76%
Thriller: chase through city streets Creative Writing Hallucination	83	80	78	77	72	78%
Detailed Writing Rules						74.28%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	68	66	65	64	62	65%
Horror: alone in an eerie place at night Creative Writing Hallucination	75	75	74	73	71	74%
Literary fiction: old friends reunite Creative Writing Hallucination	77	75	73	73	67	73%
Mystery: examining a crime scene Creative Writing Hallucination	77	75	73	68	66	72%
Romance: separated couple reunites Creative Writing Hallucination	78	75	75	69	64	72%
Thriller: chase through city streets Creative Writing Hallucination	78	76	74	73	71	74%
genre						71.74%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	74	69	66	65	65	68%
Horror: alone in an eerie place at night Creative Writing Hallucination	86	84	71	71	69	76%
Literary fiction: old friends reunite Creative Writing Hallucination	73	71	71	71	67	70%
Mystery: examining a crime scene Creative Writing Hallucination	82	78	76	74	69	76%
Romance: separated couple reunites Creative Writing Hallucination	71	70	69	67	67	69%
Thriller: chase through city streets Creative Writing Hallucination	82	79	78	73	71	77%
Novelcrafter Default Prompt						72.62%
72.88%

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	87	87	86	86	85	86%
Medium: The Hollow (Inferred) Tooling Reasoning	87	85	83	83	80	84%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	90	89	88	85	80	87%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	90	85	83	83	76	83%
84.91%

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	100	100	100	100	50	50	25	25	25	25	60%
Long text (~1594 words), small codex (11 entries) Hallucination	100	100	100	100	25	17	17	17	13	6	49%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	100	100	100	25	5	83%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	100	100	6	0	81%
basic entries											68.21%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	100	100	100	100	0	90%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	25	25	25	17	13	10	2	0	32%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	100	100	100	100	100	100%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	100	100	100	100	100	100	100	100	25	93%
detailed entries											78.53%
73.37%

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	72	70	69	55	52	51	51	51	43	43	56%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	79	79	79	79	75	74	69	61	58	57	71%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	77	76	73	72	66	61	60	60	60	53	66%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	87	87	83	80	80	76	76	72	72	72	78%
matrix											67.67%
tiers
5 codex entries Tooling Reasoning	100	93	93	93	87	87	75	75	66	66	83%
10 codex entries Tooling Reasoning	94	94	89	83	83	83	83	83	78	78	85%
20 codex entries Tooling Reasoning	82	82	82	82	79	75	73	70	69	60	75%
40 codex entries Tooling Reasoning	77	73	67	61	61	53	53	44	44	33	57%
tiers											75.09%
71.38%

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	50	50	50	50	50	50	50	50	60%
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	0	0	0	70%
Indirect birth year Reasoning	100	100	100	100	100	100	100	100	100	50	95%
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	0	0	0	0	0	0	0	0	20%
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%
82.92%

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	0	0	0	0	0	0	0	0	0	0	0%
Write 200 words with 50% dialogue Rule Following Utility	50	0	0	0	0	0	0	0	0	0	5%
Write 200 words with 90% dialogue Rule Following Utility	50	49	39	33	27	12	11	7	5	0	23%
dialogue-200											9.45%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	50	48	34	34	0	0	0	0	0	0	17%
Write 500 words with 50% dialogue Rule Following Utility	50	50	38	34	18	7	0	0	0	0	20%
Write 500 words with 70% dialogue Rule Following Utility	52	49	37	26	0	0	0	0	0	0	17%
dialogue-500											17.57%
Ungrouped
Write unattributed dialogue Rule Following	100	100	61	61	61	61	61	14	1	1	52%
18.99%

Language Comprehension

Does the model understand more than just English?

Scenario	#1	#2	#3	#4	#5	Total
Asking for directions (Dutch) Language	100	100	0	0	0	40%
Asking for directions (German) Language	100	100	0	0	0	40%
Friend got new kittens (German) Language	100	100	100	0	0	60%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
60.00%

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	100	100%
Character dialogue (Hindi) in a story Language	100	100	55	50	0	61%
Character dialogue (Italian) in a story Language	100	100	100	0	0	60%
Character dialogue (Spanish) in a story Language	100	100	100	75	50	85%
81.18%

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	97	89	76	73	63	53	45	45	27	24	59%
Write sentences with 10 words each Utility	64	52	51	38	34	31	24	15	7	7	32%
Write sentences with 20 words each Utility	8	8	7	0	0	0	0	0	0	0	2%
31.27%

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	100	100	100	100	100	100	100%
outline-count											100.00%
pov-count
Count point of views for Jack and Olivia Utility	50	50	50	50	50	50	50	0	0	0	35%
Count point of views for Jack Harper Utility	100	0	0	0	0	0	0	0	0	0	10%
Count point of views for Olivia Utility	100	0	0	0	0	0	0	0	0	0	10%
pov-count											18.33%
59.17%

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	64	61	61	58	58	50	47	57%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	98	95	95	95	90	36	87%
Combined: 3rd person past → 1st person present Text Editing	94	93	93	92	89	7	6	68%
Expand all contractions Text Editing	100	98	98	98	98	98	87	97%
Location rename: market square, outer ring, bridge, northern mines Text Editing	93	93	93	93	91	91	91	92%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	91	91	91	91	91	90	90	91%
Passive voice → active voice Text Editing Hallucination	79	78	78	78	73	73	73	76%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	97	97	97	96	95	95	95	96%
Tense rewriting: past to present Text Editing	99	99	93	93	92	86	0	80%
Generic Prompt								82.67%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	100	75	67	67	64	39	33	63%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	95	95	95	95	95	95	93	95%
Combined: 3rd person past → 1st person present Text Editing	87	87	85	85	85	85	85	86%
Expand all contractions Text Editing	100	100	99	99	99	99	99	99%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	98	96	96	96	96	97%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	91	91	91	91	91	91	91	91%
Passive voice → active voice Text Editing Hallucination	88	83	82	81	80	80	78	82%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	97	97	97	97	97	95	91	96%
Tense rewriting: past to present Text Editing	93	92	92	91	89	89	85	90%
Specific Prompt								88.78%
85.73%

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	67	97%
96.67%

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	0	0	0	0	0	0	0	0	0	0	0%
Simple Rule Following	100	0	0	0	0	0	0	0	0	0	10%
Simple (1-shot) 1-shot Rule Following	0	0	0	0	0	0	0	0	0	0	0%
Simple (5-shot) Few-shot Rule Following	0	0	0	0	0	0	0	0	0	0	0%
Unattributed dialogue Rule Following	100	100	100	0	0	0	0	0	0	0	30%
8.00%

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	0	0	0	0	0	0	40%
paragraphs											80.00%
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	98	0	0	0	0	0	0	0	0	20%
20 sentence summary Utility	0	0	0	0	0	0	0	0	0	0	0%
50 sentence summary Utility	0	0	0	0	0	0	0	0	0	0	0%
sentences											43.97%
words
10 word summary Utility	92	92	92	92	92	92	92	92	92	77	91%
20 word summary Utility	77	54	0	0	0	0	0	0	0	0	13%
50 word summary Utility	98	77	77	27	9	0	0	0	0	0	29%
100 word summary Utility	54	54	27	2	0	0	0	0	0	0	14%
200 word summary Utility	98	2	0	0	0	0	0	0	0	0	10%
words											31.29%
47.40%