NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8VDE0RZ58CE3C7MKV3TJM
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
17.5s
Cost:
$0.011246
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5011%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 rain hammered against the window of the van, and Molly checked her watch for the fourth time in as many minutes. Bill sat beside her, tapping his fingers against a clipboard covered in crayon drawings of balloons and cake. "Remind me," Bill said, "why we're stealing presents from a seven-year-old." "Because," Molly said, "Tiffany Whitmore's birthday party has forty-three presents from forty-three rich parents trying to out-gift each other. You know what that means?" "Overpriced Lego sets?" "Jewelry, Bill. Half these kids get real jewelry now. Little diamond earrings, gold bracelets. Some poor rich kid's getting a Rolex for his eighth birthday because his father can't be bothered to show up in person." Bill frowned at the clipboard. "This says there's a bouncy castle." "There's always a bouncy castle." "I don't like bouncy castles. Structurally unsound. You ever notice how they just deflate sometimes? No warning. Just—" he made a sagging motion with his hands. "Focus, Bill." He sighed and pulled out two costumes from a duffel bag—one a slightly moth-eaten clown suit, the other a fuzzy purple dinosaur outfit with a zipper down the back that looked suspiciously like it had been stolen from a mascot costume warehouse. "I am not wearing the dinosaur," Molly said. "You said last time you'd take turns." "Last time was a mall opening. This is a child's birthday party. I refuse to be a dinosaur in front of children who will remember this face for the rest of their lives." "Nobody's gonna see your face. That's the point of the costume." Molly grabbed the clown suit instead, yanking it over her black turtleneck with visible disgust. "If anyone asks, I do balloon animals." "You don't know how to make balloon animals." "I'll make one animal. A snake. Everyone can make a snake." Bill wriggled into the dinosaur suit, his head popping through the neck hole like a man surfacing from a pool of felt. "How do I look?" "Like a threat to several endangered species." "Perfect." He grabbed the giant sack meant for gifts—repurposed, poorly, from what appeared to be an old Santa costume. "Okay. Plan's simple. We entertain the kids for twenty minutes, and when they're distracted by the magician—" "There's a magician?" "Says so right here. Magician at three. We slip into the gift room, load up the sack, and walk out the side door while everyone's watching some guy pull a rabbit out of a hat." "And if someone notices forty-three presents missing?" "They won't. Not till the party's over. Kids don't count presents until they're ripping into them, and by then we'll be three towns over." Molly pulled a red rubber nose from her pocket and snapped it onto her face. "This is humiliating." "You look great. Very trustworthy. Very huggable." "I will end you, Bill." He grinned, adjusting his dinosaur tail. "Not before we hit the loot room, partner. Let's go make some kids very happy for exactly one hour before we ruin their lives." Molly sighed, opened the van door, and stepped out into the rain, clown shoes squeaking against the pavement.
created_at
"2026-07-01T07:21:17.004Z"
7/1/2026, 7:21:17 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1691
moderation_latency
(null)
generation_time
17432
tokens_prompt
77
tokens_completion
817
native_tokens_prompt
93
native_tokens_completion
1106
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
0.011246
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01HJJ1TsbGze525i91vCLeDv"
is_byok
false
latency
1688
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-1782890477-t1U2Qj0hivL9YYGPaFAM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890477-PehDor1N84Yz0Tk2PX3a"
upstream_id
"msg_01HJJ1TsbGze525i91vCLeDv"
total_cost
0.011246
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
35.00%
Matches word count
n/a
neededClean
false
words
518
0.00%
Dialogue to Total Word Ratio
Ratio: 62.21%, Deviation: 32.21%
neededClean
false
wordsTotal
524
wordsDialogue
326
17.5011%