Gemma 4 31B (Reasoning)

google/gemma-4-31b-it

Gemma 4 31B (Reasoning)

via OpenRouter

Release Date

Apr 3rd, 2026

Context Size

256k

Reasoning

Yes

Benchmark Cost

$1.10

Speed

29.5 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	81	80	79	77	73	78%
Horror: alone in an eerie place at night Creative Writing Hallucination	82	78	77	76	75	78%
Literary fiction: old friends reunite Creative Writing Hallucination	83	82	80	79	76	80%
Mystery: examining a crime scene Creative Writing Hallucination	80	80	79	78	77	79%
Romance: separated couple reunites Creative Writing Hallucination	86	82	81	81	80	82%
Thriller: chase through city streets Creative Writing Hallucination	79	79	78	78	72	77%
Detailed Writing Rules						78.98%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	78	71	67	64	64	69%
Horror: alone in an eerie place at night Creative Writing Hallucination	76	75	75	75	70	74%
Literary fiction: old friends reunite Creative Writing Hallucination	75	74	69	65	65	69%
Mystery: examining a crime scene Creative Writing Hallucination	74	74	70	70	70	72%
Romance: separated couple reunites Creative Writing Hallucination	73	71	70	68	67	70%
Thriller: chase through city streets Creative Writing Hallucination	82	79	79	76	75	78%
genre						72.05%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	88	76	76	75	67	76%
Horror: alone in an eerie place at night Creative Writing Hallucination	84	80	80	77	76	79%
Literary fiction: old friends reunite Creative Writing Hallucination	84	83	82	81	77	81%
Mystery: examining a crime scene Creative Writing Hallucination	83	81	78	78	75	79%
Romance: separated couple reunites Creative Writing Hallucination	81	78	76	76	74	77%
Thriller: chase through city streets Creative Writing Hallucination	86	83	82	81	78	82%
Novelcrafter Default Prompt						79.18%
76.74%

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	94	95%
Medium: The Hollow (Inferred) Tooling Reasoning	99	97	96	96	96	97%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	98	97	97	97	97	97%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	100	100	99	98	94	98%
96.86%

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	17	17	17	17	17	17	17	17	33%
Long text (~1594 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	100	100	100	100	100%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	100	100	100	100	25	93%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	100	100	100	100	100%
basic entries											81.46%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	100	100	100	25	25	85%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	100	100	25	25	25	25	25	25	55%
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	100	100%
detailed entries											85.00%
83.23%

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	96	96	95	95	95	94	93	91	90	86	93%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	100	98	98	98	98	97	96	91	90	89	96%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	100	100	100	100	100	97	97	92	92	87	96%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	100	100	100	100	100	100	100	100	97	97	99%
matrix											96.14%
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	100	97	96	96	96	94	92	92	92	92	95%
40 codex entries Tooling Reasoning	100	100	100	100	100	100	100	100	100	92	99%
tiers											98.48%
97.31%

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	100	100	100	0	0	0	70%
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%
97.50%

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	100	100	100	100	100	100	100	100	98	91	99%
Write 200 words with 50% dialogue Rule Following Utility	100	100	100	100	100	100	100	100	88	71	96%
Write 200 words with 90% dialogue Rule Following Utility	86	83	81	74	68	52	48	44	44	28	61%
dialogue-200											85.22%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	99	89	76	48	43	34	30	8	3	0	43%
Write 500 words with 50% dialogue Rule Following Utility	98	97	91	91	52	38	5	2	0	0	47%
Write 500 words with 70% dialogue Rule Following Utility	0	0	0	0	0	0	0	0	0	0	0%
dialogue-500											30.15%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	100	100%
63.73%

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	0	0	0	0	20%
Friend got new kittens (Tagalog) Language	100	100	100	100	0	80%
75.00%

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	67	64	64	64	58	63%
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%
92.64%

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	100	100	100	100	100	100%
100.00%

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	100	100	100	100	100	100	100	100	100	50	95%
Count point of views for Jack Harper Utility	100	100	100	100	100	100	100	100	100	100	100%
Count point of views for Olivia Utility	100	100	100	100	100	100	100	100	100	100	100%
pov-count											98.33%
99.17%

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	99	99	99	99	99	99	99%
Expand all contractions Text Editing	100	99	99	99	99	99	98	99%
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	99	99	99	99	100%
Passive voice → active voice Text Editing Hallucination	98	98	97	97	96	96	95	97%
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								99.35%
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	99	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	100	99	99	99	99	98	97	99%
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								99.85%
99.60%

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	100	100	100	0	0	80%
Simple Rule Following	100	100	100	100	100	100	100	100	100	0	90%
Simple (1-shot) 1-shot Rule Following	100	100	100	100	100	100	100	100	100	0	90%
Simple (5-shot) Few-shot Rule Following	100	100	100	100	100	100	100	100	100	100	100%
Unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	100	100	100%
92.00%

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	100	100%
50 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
sentences											99.99%
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	100	100	100	100%
100 word summary Utility	100	100	100	100	100	100	100	100	100	100	100%
200 word summary Utility	100	100	100	100	100	100	100	100	100	100	100%
words											100.00%
100.00%