NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9NMP0V8DV6Z4JCAEF4JPR
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
17.5s
Cost:
$0.010296
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 windshield of the van as Molly traced her finger along a hand-drawn map spread across her lap. Bill sat beside her, stuffing the last bite of a donut into his mouth, powdered sugar dusting his mustache like fake snow. "Okay, so the party starts at two," Molly said, not looking up. "Which means presents get piled on that table by the window at exactly one-forty-five. That's our window. Fifteen minutes." Bill swallowed. "Fifteen minutes to rob a six-year-old's birthday party." "Seven-year-old," Molly corrected. "Timmy Fitzgerald. Only child of Gary Fitzgerald, hedge fund manager, and Denise Fitzgerald, heiress to a mattress fortune. You know what that means?" "Bouncy castle?" "Money, Bill. That means the presents in that pile are going to be worth more than most people's cars." She tapped the map. "iPads. Designer sneakers in kid sizes, which is insane, by the way. And rumor has it Grandma Fitzgerald sent an envelope of bearer bonds because she doesn't trust banks." Bill squinted at the little stick figure Molly had drawn wearing what appeared to be a cape. "Who's this?" "That's you. You're the entertainment." "The what?" "Bill, we talked about this. You're dressing up as Captain Whimsy." "I am not wearing that costume again. Last time the tights gave me a wedgie I still think about." "The costume gets us in the door! Nobody questions the clown, Bill. The clown is invisible. The clown is the Trojan horse of children's parties." He crossed his arms, sugar still clinging to his mustache. "And what are you gonna be doing while I'm out there getting wedgied for the cause?" "I'm the caterer's assistant. Nobody looks twice at a woman carrying a tray of juice boxes." She rolled up the map and stuffed it into her jacket. "I slip through the crowd, get to the present table, load the duffel bag disguised as extra balloons, and we're gone before the cake even comes out." "And if someone stops you?" "Then I say I'm allergic to gluten and need to check the ingredients on the cupcakes. Works every time. Parents respect food allergies more than they respect the police." Bill sighed, looking out at the rain-streaked glass, at the massive house looming at the end of the driveway with balloons already tied to the mailbox. "You know, for a second there, I thought we'd finally gotten past robbing kids' birthday parties." "We're not robbing kids," Molly said, offended. "We're robbing rich adults who happen to have children. There's a difference." "Is there?" "Timmy's not gonna remember what he got for his seventh birthday, Bill. Nobody remembers their seventh birthday." "I remember mine. Got a bike." "Did anyone steal your bike?" Bill paused. "...No." "Then shut up and put on the wig."
created_at
"2026-07-01T07:35:36.395Z"
7/1/2026, 7:35:36 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2012
moderation_latency
(null)
generation_time
17383
tokens_prompt
77
tokens_completion
726
native_tokens_prompt
93
native_tokens_completion
1011
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
0.010296
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01C66Uoiz4UbhupNCFifE4i9"
is_byok
false
latency
2012
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-1782891336-Sn6AVUUqGk2aG1COYvaG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891336-UWaLgLnCjT2AX0d52htQ"
upstream_id
"msg_01C66Uoiz4UbhupNCFifE4i9"
total_cost
0.010296
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
0.00%
Matches word count
n/a
neededClean
false
words
462
0.00%
Dialogue to Total Word Ratio
Ratio: 72.77%, Deviation: 42.77%
neededClean
false
wordsTotal
470
wordsDialogue
342
0.0000%