NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA95W7R9CY9R7Y0QP9SPQJ
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
17.4s
Cost:
$0.010756
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
76.78%
Dialogue to Total Word Ratio
(details)
88.3836%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 back room of Bill's Pawn & Loan smelled like mothballs and burnt coffee. Molly sat on an overturned crate, flipping a balloon animal—a wilted, deflating poodle—between her fingers. "A children's party," she said. "You want us to rob a children's party." "Not rob. Liberate." Bill spread a crumpled invitation across the table like it was a bank blueprint. "Timmy Whitfield's seventh birthday. Look at this guest list. Look at it, Molly. Every kid whose daddy owns a hedge fund is gonna be there." "So?" "So the presents, Molly. Do you know what rich people buy seven-year-olds these days? I saw a wrapped box in the trunk of a Range Rover outside that had a Rolex box inside the wrapping paper. A Rolex. For a child who still eats glue." Molly tossed the poodle aside. "You're telling me our master plan, after the casino job fell through, is to steal birthday presents from toddlers." "They're not toddlers, they're first graders, there's a difference, and yes." "There's a bouncy castle, Bill. There's gonna be a clown." "I've dealt with clowns before." "You cried during that clown." "That clown had a knife inside his balloon animal, that's not the same thing." Bill jabbed a finger at the invitation. "Look, here's the plan. You go in as catering staff. Sensible shoes, hairnet, the whole bit. I go in dressed as the entertainment." "You are not a clown, Bill." "I'm a magician. There's a difference." "You don't know any magic." "I know how to make a pile of gift-wrapped Rolexes disappear into a duffel bag, that's the only trick that matters." Bill grinned, delighted with himself. "While you're serving those little cucumber sandwiches, I'll gather the kids for a magic show in the den. Wave a wand, do some patter, meanwhile you load the presents into the catering van." Molly crossed her arms. "And when Timmy Whitfield wants to open his presents and there aren't any?" "By then we're three states away." "You're going to make forty seven-year-olds cry on their friend's birthday." "They'll get new presents. Rich people always get new presents." Bill folded the invitation like a general folding a treaty. "This is the job, Molly. No security guards. No cameras except that one nanny cam shaped like a teddy bear, which, frankly, insults me that they think that'll stop us." Molly stood, brushing dust off her knees, already reaching for the hairnet on the table because some small, tired part of her knew he was right, knew there was no casino money coming, knew rent was due Friday. "If there's a piñata, I'm out." "There's always a piñata, Molly. That's just how birthdays work." "Then I want first pick of the candy that falls out." "Deal." Bill extended his hand. "Also I need you to distract the mother. She used to date my cousin, it's a whole thing." "Of course it is." Molly shook his hand anyway, sealing the fate of forty unsuspecting seven-year-olds and one very doomed pile of gifts.
created_at
"2026-07-01T07:46:16.595Z"
7/1/2026, 7:46:16 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1659
moderation_latency
(null)
generation_time
17393
tokens_prompt
77
tokens_completion
772
native_tokens_prompt
93
native_tokens_completion
1057
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
0.010756
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01U3dCadMFg9MKnzqJeZiRbr"
is_byok
false
latency
1659
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-1782891976-NDKxS4NyLkAIaxIXuUPf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891976-INqr1Bg0Em9G5qaBVfSL"
upstream_id
"msg_01U3dCadMFg9MKnzqJeZiRbr"
total_cost
0.010756
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
99.98%
Matches word count
n/a
neededClean
false
words
502
76.78%
Dialogue to Total Word Ratio
Ratio: 72.30%, Deviation: 2.30%
neededClean
false
wordsTotal
509
wordsDialogue
368
88.3836%