Ministral 3 3B - NC Bench

mistralai/ministral-3b-2512

Ministral 3 3B

via OpenRouter

Release Date

Dec 2nd, 2025

Context Size

131k

Reasoning

Benchmark Cost

$0.26

Speed

242.8 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	69	68	67	62	57	65%
Horror: alone in an eerie place at night Creative Writing Hallucination	83	83	81	80	79	81%
Literary fiction: old friends reunite Creative Writing Hallucination	84	79	76	75	71	77%
Mystery: examining a crime scene Creative Writing Hallucination	80	77	74	72	72	75%
Romance: separated couple reunites Creative Writing Hallucination	81	79	78	76	70	77%
Thriller: chase through city streets Creative Writing Hallucination	79	77	76	75	67	75%
Detailed Writing Rules						74.97%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	73	69	68	65	65	68%
Horror: alone in an eerie place at night Creative Writing Hallucination	81	80	80	77	69	77%
Literary fiction: old friends reunite Creative Writing Hallucination	80	78	75	72	72	76%
Mystery: examining a crime scene Creative Writing Hallucination	80	77	75	73	70	75%
Romance: separated couple reunites Creative Writing Hallucination	82	80	79	79	75	79%
Thriller: chase through city streets Creative Writing Hallucination	84	75	72	71	70	74%
genre						74.87%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	77	76	70	67	65	71%
Horror: alone in an eerie place at night Creative Writing Hallucination	77	77	73	68	65	72%
Literary fiction: old friends reunite Creative Writing Hallucination	82	82	82	78	68	78%
Mystery: examining a crime scene Creative Writing Hallucination	77	75	74	73	70	74%
Romance: separated couple reunites Creative Writing Hallucination	81	78	76	76	74	77%
Thriller: chase through city streets Creative Writing Hallucination	82	79	78	77	74	78%
Novelcrafter Default Prompt						75.06%
74.97%

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	90	90	89	88	88	89%
Medium: The Hollow (Inferred) Tooling Reasoning	85	84	84	83	79	83%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	88	87	87	87	82	86%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	89	86	86	85	84	86%
86.08%

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	28	27	27	26	25	25	17	4	2	1	18%
Long text (~1594 words), small codex (11 entries) Hallucination	38	32	30	30	29	29	29	29	27	1	27%
Short text (~524 words), big codex (51 entries) Hallucination	32	32	32	31	30	29	28	28	28	28	30%
Short text (~524 words), small codex (11 entries) Hallucination	31	31	29	29	29	29	29	28	27	3	26%
basic entries											25.43%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	27	26	26	25	25	25	1	0	0	0	16%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	28	28	26	26	25	2	2	1	0	0	14%
Short text (~524 words), big codex (51 detailed entries) Hallucination	29	28	28	28	27	27	26	6	1	0	20%
Short text (~524 words), small codex (11 detailed entries) Hallucination	42	38	33	29	28	28	27	26	3	1	26%
detailed entries											18.72%
22.08%

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	47	46	44	42	41	41	41	40	38	38	42%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	80	77	76	76	72	67	57	54	48	35	64%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	75	71	71	67	67	67	66	62	62	61	67%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	84	84	84	84	80	80	79	76	70	62	78%
matrix											62.77%
tiers
5 codex entries Tooling Reasoning	83	83	76	69	67	67	63	60	44	42	65%
10 codex entries Tooling Reasoning	86	56	53	52	52	49	41	41	39	37	51%
20 codex entries Tooling Reasoning	62	60	59	59	56	55	47	43	42	41	52%
40 codex entries Tooling Reasoning	83	83	83	80	75	72	71	67	60	53	73%
tiers											60.26%
61.52%

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	100	100%
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	50	50	90%
What instrument does Lucy play? Reasoning	0	0	0	0	0	0	0	0	0	0	0%
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	0	0	0	0	0	0	0	0	0	0	0%
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%
78.33%

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	98	98	92	70	50	34	9	5	5	0	46%
Write 200 words with 50% dialogue Rule Following Utility	50	34	7	7	5	3	1	0	0	0	11%
Write 200 words with 90% dialogue Rule Following Utility	68	48	22	14	1	0	0	0	0	0	15%
dialogue-200											24.04%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	52	46	13	3	2	0	0	0	0	0	12%
Write 500 words with 50% dialogue Rule Following Utility	49	48	44	25	22	3	0	0	0	0	19%
Write 500 words with 70% dialogue Rule Following Utility	22	1	0	0	0	0	0	0	0	0	2%
dialogue-500											10.99%
Ungrouped
Write unattributed dialogue Rule Following	61	61	61	61	14	14	14	14	1	0	30%
19.27%

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	0	0	0	0	0	0%
Character dialogue (German) in a story Language	100	100	90	0	0	58%
Character dialogue (Hindi) in a story Language	67	56	0	0	0	24%
Character dialogue (Italian) in a story Language	100	93	0	0	0	39%
Character dialogue (Spanish) in a story Language	100	100	100	0	0	60%
36.20%

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	93	84	74	74	64	63	56	56	52	50	66%
Write sentences with 10 words each Utility	82	78	65	64	58	56	54	53	15	7	53%
Write sentences with 20 words each Utility	23	19	10	4	2	2	0	0	0	0	6%
41.79%

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	0	0	0	0	0	50%
outline-count											83.33%
pov-count
Count point of views for Jack and Olivia Utility	100	50	50	50	50	50	50	0	0	0	40%
Count point of views for Jack Harper Utility	100	100	100	100	0	0	0	0	0	0	40%
Count point of views for Olivia Utility	100	0	0	0	0	0	0	0	0	0	10%
pov-count											30.00%
56.67%

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	69	64	61	58	58	58	58	61%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	95	95	95	95	95	95	95	95%
Combined: 3rd person past → 1st person present Text Editing	96	91	87	81	81	78	76	84%
Expand all contractions Text Editing	42	42	41	41	40	39	39	41%
Location rename: market square, outer ring, bridge, northern mines Text Editing	78	71	71	71	67	67	67	71%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	91	91	91	91	88	85	85	89%
Passive voice → active voice Text Editing Hallucination	67	64	58	57	57	49	48	57%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	77	77	75	74	60	60	58	69%
Tense rewriting: past to present Text Editing	85	79	79	75	72	71	66	75%
Generic Prompt								71.29%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	75	72	64	61	61	53	50	62%
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	92	92	92	92	91	91	91	92%
Expand all contractions Text Editing	98	97	97	97	97	97	96	97%
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	78	78	78	78	64	64	62	72%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	100	98	100%
Tense rewriting: past to present Text Editing	99	99	99	96	95	95	95	97%
Specific Prompt								91.08%
81.19%

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	0	0	0	0	0	0	0	0	0	0	0%
Simple Rule Following	0	0	0	0	0	0	0	0	0	0	0%
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	0	0	0	0	0	0	0	0	0	0	0%
0.00%

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	100	98	100%
20 sentence summary Utility	100	100	100	100	100	92	54	2	2	0	65%
50 sentence summary Utility	92	2	2	0	0	0	0	0	0	0	10%
sentences											74.85%
words
10 word summary Utility	100	100	100	100	98	98	98	98	98	77	97%
20 word summary Utility	100	100	100	100	100	100	100	100	100	98	100%
50 word summary Utility	98	54	54	2	2	0	0	0	0	0	21%
100 word summary Utility	100	92	77	54	9	0	0	0	0	0	33%
200 word summary Utility	98	0	0	0	0	0	0	0	0	0	10%
words											52.12%
71.91%