NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9SEN1XBC48R9EW5CTKBB6
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
16.7s
Cost:
$0.011346
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
15.24%
Dialogue to Total Word Ratio
(details)
57.6185%
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 apartment smelled like old pizza boxes and desperation. Molly spread a hand-drawn map across the table, weighted down on one corner by a half-empty beer can. "Okay, so the party's at the Hendricks house," Molly said. "Saturday, two o'clock. Timmy Hendricks turns seven." "Timmy Hendricks," Bill repeated, like the name offended him personally. "Who names their kid Timmy in this day and age." "Focus, Bill." "I'm focused. I'm just saying, it's a stupid name." "The presents," Molly said, jabbing the map, "are gonna be stacked in the living room. Right by the big window. I scouted it yesterday pretending to be a mom looking for the bathroom." Bill leaned back in his chair, arms crossed. "You dressed up as a mom?" "I put on a cardigan, Bill." "That's basically a costume." "It's a garment. Anyway. There's a side door off the kitchen, it leads right into the backyard where they'll have the bounce house and the clown—" "There's a clown?" "There's always a clown, Bill, it's a seven-year-old's birthday party." "I hate clowns." "Everybody hates clowns, that's not the point. The point is, while the clown's doing his balloon animal nonsense outside, everybody's attention is on the yard. Parents drinking wine out of juice boxes, kids screaming, chaos everywhere. That's our window." Bill scratched his chin. "So we just walk in the side door." "We walk in the side door," Molly confirmed. "You're wearing the pizza delivery uniform." "Why am I always the pizza guy?" "Because you have a trustworthy face for pizza. I don't know what to tell you." "I want to be the mysterious uncle this time." "There's no mysterious uncle at a seven-year-old's birthday, Bill, that's a whole different kind of crime." Bill sighed dramatically and slumped in his chair like a wounded man. "Fine. Pizza guy. Again." "You bring two empty pizza boxes, you knock on the side door, somebody lets you in because free pizza smells like free pizza, and then you just—drift. Toward the presents." "Drift." "Casually. Like you're lost. Like you're looking for the bathroom too." "Everybody's looking for the bathroom in this plan." "It's a classic cover, don't knock it." Bill picked at the beer can's tab, thinking. "And you're doing what while I'm drifting?" "I'm the mom in the cardigan, remember? I'm gonna be out back, helping herd children into the bounce house, being generally helpful and invisible. Then when the cake comes out—" "There's cake?" "There's always cake, Bill." "I love cake." "When the cake comes out, everyone's eyes go to the cake. Singing, candles, the whole show. That's when you load the bag." "What bag?" Molly pulled a folded canvas duffel from under the table and dropped it in front of him with a thud. "This bag." Bill unfolded it, held it up to the light like he was appraising a fine wine. "This is a big bag for a seven-year-old's presents." "Timmy Hendricks," Molly said solemnly, "has a lot of aunts."
created_at
"2026-07-01T07:37:41.293Z"
7/1/2026, 7:37:41 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1610
moderation_latency
(null)
generation_time
16714
tokens_prompt
77
tokens_completion
799
native_tokens_prompt
93
native_tokens_completion
1116
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
0.011346
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01PzaWFirbiENbFHAyZ6F15s"
is_byok
false
latency
1610
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-1782891461-uXXGP8RHclwsQfwRhGbI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891461-Q3DWqCkQ4bN4bFxDybml"
upstream_id
"msg_01PzaWFirbiENbFHAyZ6F15s"
total_cost
0.011346
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
100.00%
Matches word count
n/a
neededClean
false
words
499
15.24%
Dialogue to Total Word Ratio
Ratio: 76.13%, Deviation: 6.13%
neededClean
false
wordsTotal
507
wordsDialogue
386
57.6185%