NC Bench
Overview
About
Tests
Models
Model
Claude Sonnet 4.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYYBJQCFAVJMNKREVQXPN3S
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 adjusted her fake mustache in the car's rearview mirror while Bill wrestled with an enormous cardboard box decorated with dancing unicorns. The bounce house across the street wobbled with shrieking seven-year-olds, their sugar-fueled chaos providing perfect cover. "Ready?" Bill whispered. She nodded, grabbing her clipboard. They'd learned years ago that looking official opened more doors than any lockpick. Bill hoisted the empty box onto his shoulder, and they marched toward the backyard gate with the confidence of people who absolutely belonged at little Madison's birthday extravaganza. A harried mother barely glanced at them as they passed through. Molly's eyes locked onto the present table, a magnificent tower of wrapped boxes and gift bags that probably contained more iPads than a Best Buy clearance sale. Bill positioned himself strategically, his large box obscuring the view from most angles. Parents clustered near the snack table, completely absorbed in their own conversations about mortgage rates and private schools. "Now," Molly said. They worked with practiced efficiency, transferring gifts into Bill's box with the smooth coordination of a pit crew. Within ninety seconds, they were walking back through the gate, leaving behind only confused wrapping paper scraps and one suspicious clown.
created_at
"2026-02-08T15:36:44.856557+00:00"
Sunday, February 8th, 2026 at 3:36:44 PM GMT+00:00
model
"anthropic/claude-4.5-sonnet-20250929"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2121
moderation_latency
190
generation_time
8295
tokens_prompt
61
tokens_completion
249
native_tokens_prompt
75
native_tokens_completion
286
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
0.004515
router
(null)
provider_responses
0
id
"daecbe11-dfca-4d28-b640-7da584f5571c"
status
200
is_byok
false
latency
2114
endpoint_id
"d8bee848-f020-454a-b2be-4a7ce868f99f"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-sonnet-20250929"
api_type
"completions"
id
"gen-1770564995-dKxQ3JxWGd925CYisBA7"
upstream_id
"daecbe11-dfca-4d28-b640-7da584f5571c"
total_cost
0.004515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
51.8118%
Dialogue to Total Word Ratio
Ratio: 1.00%, Deviation: 9.00%
neededClean
false
wordsTotal
201
wordsDialogue
2
75.9054%