NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ94NPE42HS37VK9DMDEVSF
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.6s
Cost:
$0.004785
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.89%
Dialogue to Total Word Ratio
(details)
97.9424%
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 crouched behind the garden hedge, her black turtleneck already attracting suspicious glances from the postman. She adjusted her oversized sunglasses and consulted the hand-drawn map spread across her knees, which depicted, in alarming detail, the layout of a six year old's birthday party. Bill belly-crawled through the flower bed, leaving a trail of crushed petunias behind him. He had insisted on wearing camouflage trousers, which made him entirely invisible in a jungle environment but catastrophically obvious on a suburban lawn in Swindon. "There are more children than expected," Molly whispered. Bill pulled a pair of binoculars from his vest and surveyed the scene. A clown was making balloon animals near the back fence. A bouncy castle wobbled ominously in the breeze. The presents were stacked in a magnificent glittering pile beside the garden table, wrapped in paper so bright it was practically taunting them. He had underestimated the security. Three grandmothers sat in lawn chairs forming what appeared to be an impenetrable perimeter. "The grannies are the problem," Bill muttered. They watched in silence as one grandmother produced knitting needles from her handbag, wielding them with the quiet menace of someone who had seen considerably worse than thieves.
created_at
"2026-02-18T02:26:58.119997+00:00"
2/18/2026, 2:26:58 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1163
moderation_latency
108
generation_time
7393
tokens_prompt
77
tokens_completion
333
native_tokens_prompt
75
native_tokens_completion
304
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
0.004785
router
(null)
provider_responses
0
id
"59d20782-2e56-45aa-b91f-222245d875ca"
status
200
is_byok
false
latency
1163
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381610-ZJGsJEPkD3C7ixIcQGvQ"
upstream_id
"59d20782-2e56-45aa-b91f-222245d875ca"
total_cost
0.004785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
95.89%
Dialogue to Total Word Ratio
Ratio: 5.47%, Deviation: 4.53%
neededClean
false
wordsTotal
201
wordsDialogue
11
97.9424%