Grok 4.20 (Beta) - NC Bench

x-ai/grok-4.20-beta

Grok 4.20 (Beta)

via OpenRouter

Release Date

Mar 12th, 2026

Context Size

Reasoning

Benchmark Cost

$3.80

Speed

179.0 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	84	78	78	75	80%
Horror: alone in an eerie place at night Creative Writing Hallucination	87	86	85	85	85	86%
Literary fiction: old friends reunite Creative Writing Hallucination	94	90	89	87	81	88%
Mystery: examining a crime scene Creative Writing Hallucination	90	89	85	84	83	86%
Romance: separated couple reunites Creative Writing Hallucination	90	88	87	86	84	87%
Thriller: chase through city streets Creative Writing Hallucination	87	84	83	81	81	83%
Detailed Writing Rules						85.17%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	80	79	78	76	74	78%
Horror: alone in an eerie place at night Creative Writing Hallucination	83	82	80	78	78	80%
Literary fiction: old friends reunite Creative Writing Hallucination	88	84	82	82	81	83%
Mystery: examining a crime scene Creative Writing Hallucination	88	78	78	75	72	78%
Romance: separated couple reunites Creative Writing Hallucination	83	82	77	75	73	78%
Thriller: chase through city streets Creative Writing Hallucination	80	79	78	77	73	77%
genre						79.19%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	76	75	73	72	70	73%
Horror: alone in an eerie place at night Creative Writing Hallucination	91	87	85	83	82	86%
Literary fiction: old friends reunite Creative Writing Hallucination	89	88	87	85	75	85%
Mystery: examining a crime scene Creative Writing Hallucination	90	88	88	84	83	87%
Romance: separated couple reunites Creative Writing Hallucination	86	84	83	79	79	82%
Thriller: chase through city streets Creative Writing Hallucination	87	86	86	81	79	84%
Novelcrafter Default Prompt						82.76%
82.37%

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	96	96	95	95	96%
Medium: The Hollow (Inferred) Tooling Reasoning	96	94	92	92	91	93%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	97	96	95	95	93	95%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	99	98	98	96	95	97%
95.16%

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	31	31	29	27	26	6	3	3	1	26%
Long text (~1594 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	100	33	33	6	77%
Short text (~524 words), big codex (51 entries) Hallucination	100	38	30	30	28	10	7	5	5	3	26%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	42	35	25	25	25	17	17	49%
basic entries											44.26%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	42	33	27	5	2	2	1	1	1	21%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	30	5	5	5	4	4	4	4	26%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	33	13	10	10	10	10	10	8	30%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	42	17	17	13	13	13	10	10	7	24%
detailed entries											25.42%
34.84%

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	82	81	77	77	77	72	69	68	66	65	73%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	97	97	97	97	97	96	94	93	93	87	95%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	87	87	83	83	83	83	80	72	72	68	80%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	100	100	100	100	100	92	92	92	92	92	96%
matrix											86.07%
tiers
5 codex entries Tooling Reasoning	84	83	83	76	76	76	76	76	76	69	77%
10 codex entries Tooling Reasoning	92	86	86	86	86	86	81	79	72	72	83%
20 codex entries Tooling Reasoning	100	100	100	100	100	100	100	100	100	92	99%
40 codex entries Tooling Reasoning	88	87	87	87	79	76	75	75	71	71	80%
tiers											84.74%
85.40%

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	0	90%
Future event time Reasoning	100	100	100	100	100	100	100	100	50	50	90%
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	50	50	50	50	50	50	50	50	50	50	50%
What instrument does Lucy play? Reasoning	100	100	100	100	100	100	100	100	50	0	85%
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%
84.58%

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	50	50	50	49	48	45	43	26	10	1	37%
Write 200 words with 50% dialogue Rule Following Utility	50	50	50	50	49	47	43	38	26	0	40%
Write 200 words with 90% dialogue Rule Following Utility	100	99	68	67	50	50	48	43	0	0	53%
dialogue-200											43.33%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	50	50	49	49	45	41	22	22	1	0	33%
Write 500 words with 50% dialogue Rule Following Utility	50	49	34	7	5	1	0	0	0	0	15%
Write 500 words with 70% dialogue Rule Following Utility	45	35	30	10	10	0	0	0	0	0	13%
dialogue-500											20.16%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	61	96%
40.93%

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	0	0	60%
Asking for directions (German) Language	100	100	100	100	100	100%
Friend got new kittens (German) Language	100	100	100	100	0	80%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
85.00%

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	100	100	60	92%
Character dialogue (Italian) in a story Language	100	100	100	100	92	98%
Character dialogue (Spanish) in a story Language	100	100	100	100	93	99%
97.34%

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	98	98	83	81	78	63	90%
Write sentences with 10 words each Utility	96	94	79	79	74	70	67	67	62	62	75%
Write sentences with 20 words each Utility	66	15	11	5	3	3	2	0	0	0	10%
58.37%

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	0	0	80%
outline-count											93.33%
pov-count
Count point of views for Jack and Olivia Utility	100	100	100	100	50	50	50	0	0	0	55%
Count point of views for Jack Harper Utility	100	100	100	0	0	0	0	0	0	0	30%
Count point of views for Olivia Utility	100	100	0	0	0	0	0	0	0	0	20%
pov-count											35.00%
64.17%

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	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	99	92	92	92	92	91	91	93%
Expand all contractions Text Editing	100	100	100	99	99	99	66	95%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	100	100	100	96	99%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	100	80	80	74	74	87%
Passive voice → active voice Text Editing Hallucination	99	95	95	95	94	94	92	95%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	94	94	98%
Tense rewriting: past to present Text Editing	96	96	95	95	95	95	86	94%
Generic Prompt								95.70%
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	100	100%
Combined: 3rd person past → 1st person present Text Editing	99	99	99	99	98	96	81	96%
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	98	98	98	98	98	98	97	98%
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	100	100%
Specific Prompt								99.31%
97.50%

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	0	0	0	0	0	0	0	0	0	0	0%
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	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	0	0	0	0	0	0	0	0	0	0	0%
60.00%

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	0	90%
paragraphs											96.67%
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	100	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	98	98	98	98	77	97%
sentences											99.42%
words
10 word summary Utility	100	100	100	100	100	100	100	100	100	100	100%
20 word summary Utility	100	100	100	98	92	77	54	54	9	9	69%
50 word summary Utility	100	100	98	98	92	77	77	54	27	27	75%
100 word summary Utility	100	98	77	77	54	54	54	27	2	2	54%
200 word summary Utility	54	9	9	0	0	0	0	0	0	0	7%
words											61.22%
84.09%