Tests
This page shows the performance of each test and its scenarios.
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.
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 | Best Model | Score |
|---|---|---|
| matrix | ||
| Large codex (40 entries), long passage (1,019 words) | Z.AI GLM 5.3 (Reasoning, Max) | 98.99% |
| Large codex (40 entries), short passage (165 words) | Claude Opus 4.5 | 100.00% |
| Small codex (7 entries), long passage (734 words) | Claude Opus 4.5 | 100.00% |
| Small codex (7 entries), short passage (165 words) | Gemini 3.1 Flash Lite (Preview) | 100.00% |
| tiers | ||
| 5 codex entries | DeepSeek V4 Pro (Reasoning) | 100.00% |
| 10 codex entries | GPT-5.4 (Reasoning, Low) | 100.00% |
| 20 codex entries | Claude Opus 4.5 | 100.00% |
| 40 codex entries | Kimi K3 (Reasoning, Low) | 100.00% |
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 | Best Model | Score |
|---|---|---|
| Long: The Spire of Echoes (Dense) | Claude Opus 4.8 (Reasoning) | 99.21% |
| Medium: The Hollow (Inferred) | Claude Opus 4.8 (Reasoning) | 99.41% |
| Medium: Through the Thornveil (Scattered) | Aion 3.5 (Reasoning, High) | 99.12% |
| Short: The Rusty Lantern (Explicit) | Z.AI GLM 5.1 | 99.49% |
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.
Data extraction
Extract key details from a given block of text.
| Scenario | Best Model | Score |
|---|---|---|
| All valid emails | Gemini 3.1 Flash Lite (Reasoning) | 100.00% |
| Contextual pronoun | Muse Spark 1.1 (Reasoning, Minimal) | 100.00% |
| Fruits excluding citrus | Mistral Large 2 | 100.00% |
| Future event time | Kimi K3 (Reasoning, High) | 100.00% |
| Guess the pet | Ministral 3 3B | 100.00% |
| Highest-rated movie | DeepSeek V3 (2024-12-26) | 100.00% |
| Indirect birth year | DeepSeek V4 Flash 0731 (Reasoning, High) | 100.00% |
| What instrument does Lucy play? | GPT-5.6 Luna (Reasoning, Medium) | 100.00% |
| What's the color of the car? | Claude Sonnet 5 (Reasoning) | 100.00% |
| Who's the sister? | Muse Spark 1.1 (Reasoning, Medium) | 100.00% |
| Who's the tallest? | Gemini 3.1 Flash Lite | 100.00% |
Dialogue tags
Various tasks related to dialogue tags in text.
| Scenario | Best Model | Score |
|---|---|---|
| dialogue-200 | ||
| Write 200 words with 10% dialogue | Gemini 3.8 Flash (Reasoning, Medium) | 100.00% |
| Write 200 words with 50% dialogue | Gemini 3.8 Flash (Reasoning, Medium) | 100.00% |
| Write 200 words with 90% dialogue | Muse Spark 1.3 (Reasoning, Medium) | 100.00% |
| dialogue-500 | ||
| Write 500 words with 30% dialogue | Qwen 3.8 Max (Reasoning, XHigh) | 100.00% |
| Write 500 words with 50% dialogue | Gemini 3.1 Pro (Preview) | 100.00% |
| Write 500 words with 70% dialogue | Qwen 3.8 Max (Reasoning, XHigh) | 100.00% |
| Ungrouped | ||
| Write unattributed dialogue | Qwen 3.8 Flash (Reasoning) | 100.00% |
Language Comprehension
Does the model understand more than just English?
Language Writing
Can the model generate text in different languages?
Novel outline
Handle questions about the outline of a novel in various formats
| Scenario | Best Model | Score |
|---|---|---|
| outline-count | ||
| Count acts | DeepSeek V4 Flash (Reasoning) | 100.00% |
| Count chapters | DeepSeek V4 Pro | 100.00% |
| Count scenes | GPT-5.5 (Reasoning, Low) | 100.00% |
| pov-count | ||
| Count point of views for Jack and Olivia | Qwen 3.6 35B | 100.00% |
| Count point of views for Jack Harper | GPT-5.4 (Reasoning) | 100.00% |
| Count point of views for Olivia | Gemini 3 Flash (Preview, Reasoning) | 100.00% |
Tool usage within Novelcrafter
Output messages that are related to tool usage within Novelcrafter
| Scenario | Best Model | Score |
|---|---|---|
| Create alternate prose sections | Grok 4.5 (Reasoning, Low) | 100.00% |
Relationship tree
Extracts a deterministic XML family and relationship tree from cumulative literary prose.
| Scenario | Best Model | Score |
|---|---|---|
| Core relationship tree | GPT-5.6 Sol (Reasoning, Medium) | 99.37% |
| Family relationship tree | Gemini 3.8 Flash (Reasoning, Medium) | 94.08% |
N-Length Sentences
Write sentences with exactly N words
| Scenario | Best Model | Score |
|---|---|---|
| Write sentences with 5 words each | Gemini 3 Flash (Preview) | 100.00% |
| Write sentences with 10 words each | Gemini 3.8 Flash (Reasoning, Medium) | 100.00% |
| Write sentences with 20 words each | Muse Spark 1.2 (Reasoning, Medium) | 100.00% |
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.
Voice/dialogue sheets
Extract dialogue from given text as voice sheets.
| Scenario | Best Model | Score |
|---|---|---|
| Multiple speakers | Gemma 4 31B | 100.00% |
| Simple | Gemma 4 31B | 100.00% |
| Simple (1-shot) | Grok 4.20 | 100.00% |
| Simple (5-shot) | Muse Spark 1.1 (Reasoning, Minimal) | 100.00% |
| Unattributed dialogue | GPT-6 Sol (Reasoning, Medium) | 100.00% |
Write N of X
Write exactly N words/sentences/paragraphs...
| Scenario | Best Model | Score |
|---|---|---|
| paragraphs | ||
| 1 paragraph summary | Gemma 4 31B (Reasoning) | 100.00% |
| 3 paragraph summary | Gemini 3.5 Flash (Reasoning, Minimal) | 100.00% |
| 5 paragraph summary | GPT-5 | 100.00% |
| sentences | ||
| 1 sentence summary | Qwen 3 235B A22B Instruct 2507 | 100.00% |
| 3 sentence summary | DeepSeek-V2 Chat | 100.00% |
| 10 sentence summary | DeepSeek V4 Pro (Reasoning) | 100.00% |
| 20 sentence summary | DeepSeek V4.1 Flash (Reasoning, High) | 100.00% |
| 50 sentence summary | GPT-5.1 | 100.00% |
| words | ||
| 10 word summary | Muse Spark 1.2 (Reasoning, Medium) | 100.00% |
| 20 word summary | Kimi K3 (Reasoning, High) | 100.00% |
| 50 word summary | Kimi K2.5 | 100.00% |
| 100 word summary | DeepSeek V4 Pro 0813 (Reasoning, High) | 100.00% |
| 200 word summary | Claude Opus 4.6 (Reasoning) | 100.00% |