NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA2NBD62MS1EHGC748A98K
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.2s
Cost:
$0.004596
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
20.94%
Dialogue to Total Word Ratio
(details)
60.4613%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 warehouse smelled of stale coffee and desperation, which suited Molly and Bill just fine since that described their careers accurately. Spread across the table between them was a hand-drawn map of the Hendricks residence, complete with a suspiciously detailed rendering of a bounce house. Bill traced a finger along the fence line. "Bounce house is our blind spot." Molly nodded, chewing the end of a pencil like it owed her money. She'd spent three days casing this job—a seven-year-old's birthday party with, according to her sources, an obscene pile of gifts stacked in the garage. Nintendo Switches. Drones. A hoverboard, for God's sake. Seven-year-olds didn't need hoverboards. Molly needed a hoverboard. "Clown's a problem," Bill added, sliding a photograph across the table. The clown in question had a face like a fist and forearms like a dockworker. "We wait till the piñata," Molly said. "Everyone's distracted. Kids swinging bats, parents filming, clown's corralling the mob. That's our window." Bill studied her, unconvinced. "You want to rob children." "I want to rob their parents," Molly corrected. "The children are collateral." Bill sighed, already reaching for his balaclava. Some jobs you didn't love. You just needed the money.
created_at
"2026-07-01T07:42:43.063Z"
7/1/2026, 7:42:43 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2107
moderation_latency
(null)
generation_time
9634
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
93
native_tokens_completion
441
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
0.004596
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01PeWuB3gVKauVkGfozCK4sD"
is_byok
false
latency
2107
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-1782891763-mNuetLHRnAo5Q6pw5brA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891763-HyBBAR0jHD9CTaqvMmf2"
upstream_id
"msg_01PeWuB3gVKauVkGfozCK4sD"
total_cost
0.004596
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
198
20.94%
Dialogue to Total Word Ratio
Ratio: 21.18%, Deviation: 11.18%
neededClean
false
wordsTotal
203
wordsDialogue
43
60.4613%