NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTVZXCY3P1H43FERBA4M9H
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.8s
Cost:
$0.011490
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
83.49%
Dialogue to Total Word Ratio
(details)
91.7052%
Overall
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 sticky diner table, weighing the corners down with ketchup bottles and a half-eaten plate of hash browns. The layout of the Chuckles the Clown Party Palace looked deceptively simple, but she knew better. Ball pits were tactical nightmares. Bill leaned in, squinting through his reading glasses, which he'd stolen last Tuesday from a librarian who probably hadn't even noticed yet. The party in question belonged to one Timothy Weatherford, age seven, whose father happened to be a hedge fund manager with a gift-giving problem. Word on the street was that little Timmy's guest list read like a Forbes nursery-school edition, and every pint-sized attendee was expected to arrive bearing tribute. "That's a lot of Legos," Bill murmured. Molly tapped the emergency exit with a chipped fingernail. Their plan hinged on timing: strike during the piƱata, when chaos reigned and adults were distracted by flying candy shrapnel. She'd dress as a face painter. Bill would pose as the balloon animal guy, though his twisted creations tended to resemble anatomical diagrams more than giraffes. "Kids bite," he added, rubbing an old scar. She smiled grimly and circled the loot table in red Sharpie.
created_at
"2026-04-24T13:29:04.696Z"
4/24/2026, 1:29:04 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
832
moderation_latency
(null)
generation_time
7683
tokens_prompt
77
tokens_completion
316
native_tokens_prompt
98
native_tokens_completion
440
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
usage
0.01149
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"e4adf439-eb34-40fe-93f6-f17474403898"
is_byok
false
latency
832
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777037344-NM9iFFh8XdpF7az21Erz"
session_id
(null)
api_type
"completions"
id
"gen-1777037344-UI7MPvkDk7KI4Bwc3OZl"
upstream_id
"e4adf439-eb34-40fe-93f6-f17474403898"
total_cost
0.01149
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
83.49%
Dialogue to Total Word Ratio
Ratio: 3.48%, Deviation: 6.52%
neededClean
false
wordsTotal
201
wordsDialogue
7
91.7052%