Claude Haiku 5.5 (Reasoning, Low)

anthropic/claude-haiku-5.5

Claude Haiku 5.5 (Reasoning, Low)

via OpenRouter

Release Date

Oct 7th, 2026

Context Size

Reasoning

Yes

Benchmark Cost

$0.25

Speed

141.8 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	Total
Detailed Writing Rules
Fantasy: entering an ancient ruin Creative Writing Hallucination	90	90	86	–	89%
Horror: alone in an eerie place at night Creative Writing Hallucination	92	91	88	–	90%
Literary fiction: old friends reunite Creative Writing Hallucination	87	80	78	–	82%
Mystery: examining a crime scene Creative Writing Hallucination	90	89	–	–	90%
Romance: separated couple reunites Creative Writing Hallucination	96	–	–	–	96%
Thriller: chase through city streets Creative Writing Hallucination	94	89	–	–	92%
Detailed Writing Rules					89.62%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	85	85	85	–	85%
Horror: alone in an eerie place at night Creative Writing Hallucination	96	84	81	–	87%
Literary fiction: old friends reunite Creative Writing Hallucination	85	–	–	–	85%
Mystery: examining a crime scene Creative Writing Hallucination	–	–	–	–	–
Romance: separated couple reunites Creative Writing Hallucination	–	–	–	–	–
Thriller: chase through city streets Creative Writing Hallucination	86	–	–	–	86%
genre					85.55%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	93	89	88	–	90%
Horror: alone in an eerie place at night Creative Writing Hallucination	–	–	–	–	–
Literary fiction: old friends reunite Creative Writing Hallucination	90	90	88	85	88%
Mystery: examining a crime scene Creative Writing Hallucination	87	86	–	–	87%
Romance: separated couple reunites Creative Writing Hallucination	85	84	–	–	85%
Thriller: chase through city streets Creative Writing Hallucination	91	89	–	–	90%
Novelcrafter Default Prompt					87.90%
87.96%

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	Total
Long: The Spire of Echoes (Dense) Tooling Reasoning	97	96	96	96%
Medium: The Hollow (Inferred) Tooling Reasoning	95	–	–	95%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	97	96	–	96%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	98	94	–	96%
95.91%

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	Total
basic entries
Long text (~1594 words), big codex (51 entries) Hallucination	100	100	100	100	100	–	–	100%
Long text (~1594 words), small codex (11 entries) Hallucination	100	100	–	–	–	–	–	100%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	100	100	100%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	100	–	–	–	100%
basic entries								100.00%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	100	100	100	–	–	–	100%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	–	–	–	–	–	100%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	100	–	–	–	–	100%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	100	–	–	–	–	–	100%
detailed entries								100.00%
100.00%

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	Total
matrix
Large codex (40 entries), long passage (1,019 words) Tooling Reasoning	94	83	–	–	–	–	88%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	96	92	87	87	87	87	90%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	97	97	97	92	–	–	95%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	100	100	100	–	–	–	100%
matrix							93.38%
tiers
5 codex entries Tooling Reasoning	100	83	–	–	–	–	92%
10 codex entries Tooling Reasoning	100	100	100	86	86	–	94%
20 codex entries Tooling Reasoning	89	89	81	–	–	–	86%
40 codex entries Tooling Reasoning	34	–	–	–	–	–	34%
tiers							76.61%
85.00%

Data extraction

Extract key details from a given block of text.

Scenario	#1	#2	#3	#4	#5	#6	Total
All valid emails Utility	100	100	100	–	–	–	100%
Contextual pronoun Utility	100	100	100	100	100	100	100%
Fruits excluding citrus Utility	100	100	100	100	–	–	100%
Future event time Reasoning	100	50	50	50	–	–	63%
Guess the pet Reasoning	100	100	100	–	–	–	100%
Highest-rated movie Reasoning	100	100	100	–	–	–	100%
Indirect birth year Reasoning	100	100	100	100	100	–	100%
What instrument does Lucy play? Reasoning	100	–	–	–	–	–	100%
What's the color of the car? Utility	100	100	100	100	100	–	100%
Who's the sister? Reasoning	100	100	100	–	–	–	100%
Who's the tallest? Reasoning	100	100	100	–	–	–	100%
96.59%

Dialogue tags

Various tasks related to dialogue tags in text.

Scenario	#1	#2	#3	#4	Total
dialogue-200
Write 200 words with 10% dialogue Rule Following Utility	93	86	50	–	76%
Write 200 words with 50% dialogue Rule Following Utility	0	–	–	–	0%
Write 200 words with 90% dialogue Rule Following Utility	41	18	18	18	24%
dialogue-200					33.49%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	0	0	0	–	0%
Write 500 words with 50% dialogue Rule Following Utility	0	0	–	–	0%
Write 500 words with 70% dialogue Rule Following Utility	8	0	–	–	4%
dialogue-500					1.30%
Ungrouped
Write unattributed dialogue Rule Following	61	61	61	–	61%
23.57%

Language Comprehension

Does the model understand more than just English?

Scenario	#1	#2	#3	Total
Asking for directions (Dutch) Language	100	100	–	100%
Asking for directions (German) Language	100	100	–	100%
Friend got new kittens (German) Language	100	100	100	100%
Friend got new kittens (Tagalog) Language	100	100	–	100%
100.00%

Language Writing

Can the model generate text in different languages?

Scenario	#1	#2	#3	#4	Total
Character dialogue (French) in a story Language	100	–	–	–	100%
Character dialogue (German) in a story Language	100	–	–	–	100%
Character dialogue (Hindi) in a story Language	100	96	–	–	98%
Character dialogue (Italian) in a story Language	100	–	–	–	100%
Character dialogue (Spanish) in a story Language	100	100	100	95	99%
99.30%

N-Length Sentences

Write sentences with exactly N words

Scenario	#1	#2	#3	#4	#5	#6	Total
Write sentences with 5 words each Utility	100	100	–	–	–	–	100%
Write sentences with 10 words each Utility	87	73	56	55	54	43	62%
Write sentences with 20 words each Utility	100	100	100	–	–	–	100%
87.19%

Novel outline

Handle questions about the outline of a novel in various formats

Scenario	#1	#2	#3	#4	#5	#6	#7	Total
outline-count
Count acts Utility	100	100	100	100	100	100	100	100%
Count chapters Utility	100	100	100	100	100	100	–	100%
Count scenes Utility	0	0	0	–	–	–	–	0%
outline-count								66.67%
pov-count
Count point of views for Jack and Olivia Utility	100	100	–	–	–	–	–	100%
Count point of views for Jack Harper Utility	100	100	100	100	100	–	–	100%
Count point of views for Olivia Utility	100	100	100	100	100	100	–	100%
pov-count								100.00%
83.33%

Relationship tree

Extracts a deterministic XML family and relationship tree from cumulative literary prose.

Scenario	#1	#2	Total
Core relationship tree Tooling Reasoning Hallucination	86	85	86%
Family relationship tree Tooling Reasoning Hallucination	–	–	–
85.62%

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	Total
Generic Prompt
Avoid said/asked/replied/answered Text Editing	100	100	100	100	–	–	100%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	–	–	–	–	–	–	–
Combined: 3rd person past → 1st person present Text Editing	99	99	99	–	–	–	99%
Expand all contractions Text Editing	95	95	–	–	–	–	95%
Location rename: market square, outer ring, bridge, northern mines Text Editing	96	96	96	–	–	–	96%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	99	–	–	–	–	100%
Passive voice → active voice Text Editing Hallucination	–	–	–	–	–	–	–
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	–	–	100%
Tense rewriting: past to present Text Editing	99	–	–	–	–	–	99%
Generic Prompt							98.44%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	100	100	–	–	–	–	100%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	–	–	–	100%
Combined: 3rd person past → 1st person present Text Editing	99	–	–	–	–	–	99%
Expand all contractions Text Editing	100	100	100	99	98	–	100%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	–	–	–	100%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	–	–	–	–	100%
Passive voice → active voice Text Editing Hallucination	98	97	–	–	–	–	97%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	100	100%
Tense rewriting: past to present Text Editing	100	–	–	–	–	–	100%
Specific Prompt							99.58%
99.08%

Tool usage within Novelcrafter

Output messages that are related to tool usage within Novelcrafter

Scenario	#1	#2	#3	Total
Create alternate prose sections Tooling	100	100	100	100%
100.00%

Voice/dialogue sheets

Extract dialogue from given text as voice sheets.

Scenario	#1	#2	#3	#4	#5	Total
Multiple speakers Rule Following	0	0	0	0	–	0%
Simple Rule Following	0	0	0	0	–	0%
Simple (1-shot) 1-shot Rule Following	100	100	100	–	–	100%
Simple (5-shot) Few-shot Rule Following	100	100	100	100	100	100%
Unattributed dialogue Rule Following	0	0	0	0	–	0%
40.00%

Write N of X

Write exactly N words/sentences/paragraphs...

Scenario	#1	#2	#3	#4	#5	#6	#7	Total
paragraphs
1 paragraph summary Utility	100	100	100	–	–	–	–	100%
3 paragraph summary Utility	100	–	–	–	–	–	–	100%
5 paragraph summary Utility	100	–	–	–	–	–	–	100%
paragraphs								100.00%
sentences
1 sentence summary Utility	100	100	100	100	100	–	–	100%
3 sentence summary Utility	100	100	100	100	–	–	–	100%
10 sentence summary Utility	100	100	100	100	–	–	–	100%
20 sentence summary Utility	100	92	92	54	27	–	–	73%
50 sentence summary Utility	100	100	100	100	98	–	–	100%
sentences								94.55%
words
10 word summary Utility	92	92	77	9	0	–	–	54%
20 word summary Utility	98	0	0	–	–	–	–	33%
50 word summary Utility	100	100	100	100	100	100	100	100%
100 word summary Utility	100	100	100	100	–	–	–	100%
200 word summary Utility	100	100	0	–	–	–	–	67%
words								70.73%
86.64%