NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEACYEWV7XHNXQ6SXM03NEJ
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.3s
Cost:
$0.004796
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
69.62%
Dialogue to Total Word Ratio
(details)
84.5006%
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
The warehouse smelled of stale popcorn and desperation, which suited Bill just fine since those were his two favorite things after money. He spread the blueprints across a folding table that wobbled like a drunk flamingo, jabbing his finger at a crude drawing of a suburban backyard. "The intel says twelve presents, minimum," Bill said, adjusting his fake mustache for the fourth time in as many minutes. "Bounce house is a blind spot. We go in through there." Molly leaned over the table, her eyes narrowing with the intensity of a surgeon planning an operation, if that surgeon also moonlighted as a criminal. She'd spent three weeks infiltrating a birthday party planning forum to nail down the exact timeline of pin-the-tail-on-the-donkey. "There's a piƱata," she said gravely. "Full of candy. We take that too." Bill nodded solemnly, as if she'd just informed him of a rival gang's territory. Stealing from six-year-olds required the same tactical precision as any bank job, arguably more, since six-year-olds had surprisingly loyal parents and questionable trust in strangers wearing clown costumes. "Clowns," Molly muttered, already sliding into her oversized shoes. "Nobody suspects the clowns." Bill grinned, painting on his final layer of face paint. "That's exactly what makes us dangerous."
created_at
"2026-07-01T07:48:20.068Z"
7/1/2026, 7:48:20 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1953
moderation_latency
(null)
generation_time
9318
tokens_prompt
77
tokens_completion
337
native_tokens_prompt
93
native_tokens_completion
461
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"
service_tier
"default"
usage
0.004796
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01CxHZedndTEthAm2VLiHYrZ"
is_byok
false
latency
1951
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782892100-INzsIRLRxyga2Snr5bdy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892100-r0S37ZrddwP12T22AoOW"
upstream_id
"msg_01CxHZedndTEthAm2VLiHYrZ"
total_cost
0.004796
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
69.62%
Dialogue to Total Word Ratio
Ratio: 17.76%, Deviation: 7.76%
neededClean
false
wordsTotal
214
wordsDialogue
38
84.5006%