NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTTMM7RKXTZGX9D6V2V4VK
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.6s
Cost:
$0.011290
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
83.81%
Dialogue to Total Word Ratio
(details)
91.2627%
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 unfurled the blueprints across the hood of the minivan, pinning down the corners with juice boxes. The floor plan of the Peterson residence sprawled before them in meticulous detail, every bounce house and piƱata accounted for. Bill squinted through his binoculars at the backyard, where a clown was currently twisting balloons into what appeared to be either a giraffe or a tragic cautionary tale. "Magicians are the worst witnesses," Bill muttered. The operation required precision. Seven-year-old Timmy Peterson was turning the big eight, and according to their intel, his relatives had wildly overestimated his emotional maturity. Gifts were piled three feet high on the patio table, glittering in wrapping paper like stolen treasure from a particularly glitter-obsessed pharaoh. Molly traced their entry point with a french fry. They'd pose as the entertainment, a husband-and-wife magic duo called The Astonishing Astonishments, and during the disappearing rabbit trick, the presents themselves would disappear. Bill would distract the parents with overly complicated card tricks while Molly loaded the getaway van, disguised cleverly as an ice cream truck. "One problem," Molly said. Neither of them knew any magic tricks. They had six hours and a library card.
created_at
"2026-04-24T13:28:20.375Z"
4/24/2026, 1:28:20 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
636
moderation_latency
(null)
generation_time
7497
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
98
native_tokens_completion
432
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
0.01129
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"ee27a3d9-b8ac-4720-8314-c71453f9c7d5"
is_byok
false
latency
636
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-1777037300-fVc7BsUYV2ft4d68DadH"
session_id
(null)
api_type
"completions"
id
"gen-1777037300-SlFm1onm2BwURhzLk4VW"
upstream_id
"ee27a3d9-b8ac-4720-8314-c71453f9c7d5"
total_cost
0.01129
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
83.81%
Dialogue to Total Word Ratio
Ratio: 3.52%, Deviation: 6.48%
neededClean
false
wordsTotal
199
wordsDialogue
7
91.2627%