NC Bench
Overview
About
Tests
Models
Model
Claude Haiku 4.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYY522DECBRVTWVYHTBKR3R
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly spread the blueprints across the kitchen table, her finger tracing the layout of the community center's gymnasium. Outside, children's laughter echoed like tiny alarm bells. "The presents are stacked by the gift table," she muttered, studying the floor plan with the intensity of a general planning an invasion. Bill walked in carrying two oversized teddy bears, their fur matted from the costume rental place. He dropped them unceremoniously onto the couch. "I found the perfect disguise," he announced proudly. "Those are ridiculous," Molly said, barely glancing up. "Exactly. No one suspects a ridiculous teddy bear," Bill replied, grinning at his own logic. Molly sighed and returned to the blueprints. The security consisted entirely of one overwhelmed parent and a malfunctioning camera that pointed at the snack table. She'd already confirmed this through three hours of reconnaissance disguised as a concerned grandmother. They would enter at three o'clock precisely, during the piƱata chaos when every adult's attention would be focused on preventing sugar-induced violence among six-year-olds. Bill would create a distraction near the entrance while Molly stuffed the presents into a laundry basket marked "Decorations." By four o'clock, they'd be gone with enough toys to supply a small black market operation for months.
created_at
"2026-02-08T15:33:06.568637+00:00"
Sunday, February 8th, 2026 at 3:33:06 PM GMT+00:00
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
966
moderation_latency
134
generation_time
3906
tokens_prompt
61
tokens_completion
259
native_tokens_prompt
75
native_tokens_completion
310
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.001625
router
(null)
provider_responses
0
id
"3380deba-9e09-41a6-87d9-efe4325b02e6"
status
200
is_byok
false
latency
965
endpoint_id
"d000261c-5aeb-47d1-ac87-ad64dbe1cdb6"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770564782-ClcvpJQjAcuEuKUpztJA"
upstream_id
"3380deba-9e09-41a6-87d9-efe4325b02e6"
total_cost
0.001625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
206
99.7921%
Dialogue to Total Word Ratio
Ratio: 12.14%, Deviation: 2.14%
neededClean
false
wordsTotal
206
wordsDialogue
25
99.2522%