NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE90W77QWJ0DGB519H5E43B
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
18.2s
Cost:
$0.011146
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
96.97%
Dialogue to Total Word Ratio
(details)
93.7259%
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 of the van smelled like stale coffee and Bill's cologne, which he insisted was called "Midnight Thunder" but smelled more like a gas station air freshener. Molly sat cross-legged on a crate, studying a crumpled piece of paper with the precision of a general reviewing battle plans. "So let me get this straight," Bill said, arms folded. "We're robbing a six-year-old's birthday party." "We're not robbing a six-year-old," Molly said. "We're robbing forty presents that belong to a six-year-old. There's a difference." "Is there?" "Yes. One sounds like a crime against children. The other sounds like a crime against Toys R Us. I prefer the second narrative." Bill rubbed his temples. "Molly, there's gonna be a bounce house." "I love bounce houses." "There's gonna be a clown." "I hate clowns, but that's not the point." "There's gonna be forty screaming children who will absolutely notice two adults stuffing Barbie dolls into a duffel bag." Molly held up a finger. "This is why we have costumes." She reached into a bag and pulled out two costumes, tossing one to Bill. He unfolded it slowly, horror dawning on his face. "Molly. This is a dinosaur costume." "It's a raptor. Very popular with kids right now." "I look like a green trash bag had a baby with a chicken." "You look like Rex, party entertainer extraordinaire, here to make balloon animals and steal literally everything of value in the backyard." Bill stared at her. "This is insane. Even for us." "Bill, we've robbed banks." "Banks don't have moms watching." "Moms are easy. Moms are exhausted. Moms haven't slept since 2019. We walk in, we do the raptor dance, we distract with balloon swords, and I sneak the presents into the van through the side gate." "And what if a kid asks Rex the Raptor to do a magic trick?" "Then Rex the Raptor learns real fast how to disappear." Bill groaned, pulling the costume over his shoulders, wriggling his arms into the sleeves. The tail dragged pathetically behind him, brushing dust off the van floor. "I feel ridiculous." "You look majestic. A predator among sheep. Well—children." "There's something deeply wrong with you." "There's something deeply broke with us, and this fixes that. Forty presents, resold quietly, no one's the wiser. Kid gets attention from a real dinosaur, parents get an unforgettable memory, we get rent money. Everybody wins." "Except the kid. Who loses literally every present." Molly paused, tilting her head, considering. "Okay, fine, we leave him one. The biggest one. We're thieves, not monsters." Bill zipped up the costume with a defeated sigh, his voice muffled beneath green fabric. "If we get arrested in dinosaur costumes, I swear—" "They won't arrest Rex," Molly said, grinning as she slipped on her own bright pink tutu, adjusting her fairy wings. "Especially not when Tinkerbell's giving out cupcakes." "You're insufferable." "I'm resourceful. Now come on, Rex. We've got a party to crash."
created_at
"2026-07-01T07:24:15.985Z"
7/1/2026, 7:24:15 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1836
moderation_latency
(null)
generation_time
18143
tokens_prompt
77
tokens_completion
792
native_tokens_prompt
93
native_tokens_completion
1096
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
0.011146
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01NhxwUvdkmr3qg3as3Xcg97"
is_byok
false
latency
1836
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-1782890655-1jBA79ke5h3IjuY2bsTh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890655-120wpqlwjiEAKotpWtNm"
upstream_id
"msg_01NhxwUvdkmr3qg3as3Xcg97"
total_cost
0.011146
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
90.48%
Matches word count
n/a
neededClean
false
words
490
96.97%
Dialogue to Total Word Ratio
Ratio: 69.22%, Deviation: 0.78%
neededClean
false
wordsTotal
497
wordsDialogue
344
93.7259%