Gemma 4 26B - NC Bench

google/gemma-4-26b-a4b-it

Gemma 4 26B

via OpenRouter

Release Date

Apr 3rd, 2026

Context Size

256k

Reasoning

Benchmark Cost

$0.34

Speed

45.8 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	73	72	72	69	68	71%
Horror: alone in an eerie place at night Creative Writing Hallucination	80	77	76	73	70	75%
Literary fiction: old friends reunite Creative Writing Hallucination	81	78	77	76	73	77%
Mystery: examining a crime scene Creative Writing Hallucination	82	78	78	75	73	77%
Romance: separated couple reunites Creative Writing Hallucination	84	82	81	78	64	78%
Thriller: chase through city streets Creative Writing Hallucination	80	75	75	73	73	75%
Detailed Writing Rules						75.53%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	72	69	64	62	62	66%
Horror: alone in an eerie place at night Creative Writing Hallucination	70	68	62	62	59	64%
Literary fiction: old friends reunite Creative Writing Hallucination	78	75	73	70	64	72%
Mystery: examining a crime scene Creative Writing Hallucination	77	72	71	66	60	69%
Romance: separated couple reunites Creative Writing Hallucination	75	72	70	69	66	71%
Thriller: chase through city streets Creative Writing Hallucination	71	71	68	65	64	68%
genre						68.23%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	78	77	76	75	74	76%
Horror: alone in an eerie place at night Creative Writing Hallucination	82	75	73	73	72	75%
Literary fiction: old friends reunite Creative Writing Hallucination	86	83	80	80	76	81%
Mystery: examining a crime scene Creative Writing Hallucination	81	81	79	77	76	79%
Romance: separated couple reunites Creative Writing Hallucination	83	80	80	79	74	79%
Thriller: chase through city streets Creative Writing Hallucination	85	84	82	80	79	82%
Novelcrafter Default Prompt						78.66%
74.14%

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	86	3	3	57%
Medium: The Hollow (Inferred) Tooling Reasoning	95	94	94	93	92	94%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	95	95	94	94	3	76%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	97	97	96	95	95	96%
80.54%

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	42	31	31	13	8	7	6	6	6	6	15%
Long text (~1594 words), small codex (11 entries) Hallucination	100	50	50	50	50	42	42	25	25	25	46%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	100	100	100	100	50	95%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	100	100	100	100	100%
basic entries											64.07%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	38	33	17	17	17	17	17	17	13	8	19%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	100	100	42	42	38	32	32	13	60%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	100	100	100	50	25	88%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	100	100	100	100	100	100	100	100	100	100%
detailed entries											66.61%
65.34%

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	86	86	85	85	85	85	85	81	81	80	84%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	89	89	89	0	0	0	0	0	0	0	27%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	93	93	93	93	88	88	88	88	88	88	90%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	97	97	97	97	97	97	97	97	97	97	97%
matrix											74.36%
tiers
5 codex entries Tooling Reasoning	100	100	100	100	100	100	100	100	100	100	100%
10 codex entries Tooling Reasoning	100	100	100	100	100	100	100	100	100	100	100%
20 codex entries Tooling Reasoning	88	85	85	85	85	85	85	81	81	81	84%
40 codex entries Tooling Reasoning	92	92	92	92	92	92	92	92	83	0	82%
tiers											91.44%
82.90%

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	100	100	100	100	100	100	100	100	100	100	100%
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	100	0	0	0	0	0	0	40%
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%
95.00%

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	96	88	84	82	80	78	64	51	49	37	71%
Write 200 words with 50% dialogue Rule Following Utility	45	43	26	22	18	14	5	3	0	0	18%
Write 200 words with 90% dialogue Rule Following Utility	98	93	75	63	60	59	51	28	26	20	57%
dialogue-200											48.49%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	30	30	0	0	0	0	0	0	0	0	6%
Write 500 words with 50% dialogue Rule Following Utility	0	0	0	0	0	0	0	0	0	0	0%
Write 500 words with 70% dialogue Rule Following Utility	14	2	0	0	0	0	0	0	0	0	2%
dialogue-500											2.53%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	100	100%
36.15%

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	0	0	60%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
90.00%

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	78	96%
Character dialogue (Hindi) in a story Language	100	88	70	60	56	75%
Character dialogue (Italian) in a story Language	100	100	100	100	100	100%
Character dialogue (Spanish) in a story Language	100	100	100	100	100	100%
94.03%

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	100	100	100	100	100%
Write sentences with 10 words each Utility	100	100	100	100	100	100	100	100	100	100	100%
Write sentences with 20 words each Utility	100	100	100	100	100	92	92	74	61	61	88%
95.98%

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	0	0	0	0	0	0	0	0	20%
outline-count											73.33%
pov-count
Count point of views for Jack and Olivia Utility	100	100	100	100	100	100	0	0	0	0	60%
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	0	0	0	0	0	0	0	30%
pov-count											46.67%
60.00%

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	99	99	99	99	99	99	99%
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	96	96	96	95	95	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	99	99	99	99	99	99	99	99%
Generic Prompt								99.31%
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	100	100	100	100	100	100	99	100%
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	96	96	96	94	94	93	92	94%
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								99.37%
99.34%

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	33	93%
93.33%

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	100	100	100	100	100	100%
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	0	0	0	0	0	50%
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	100	100	100	100	100%
88.00%

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	100	100%
20 sentence summary Utility	100	100	100	100	100	100	100	100	100	92	99%
50 sentence summary Utility	100	100	100	77	54	54	2	2	0	0	49%
sentences											89.58%
words
10 word summary Utility	100	100	100	100	100	100	100	100	100	100	100%
20 word summary Utility	100	100	100	100	100	100	100	100	100	100	100%
50 word summary Utility	100	100	100	100	100	100	100	98	98	92	99%
100 word summary Utility	100	98	98	98	98	92	92	92	92	92	95%
200 word summary Utility	9	2	2	0	0	0	0	0	0	0	1%
words											79.11%
87.96%