NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE96EE6DVEQ3J809JWE7X3D
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.5s
Cost:
$0.005036
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly spread the blueprint across the tableāa crayon drawing of a house with a lopsided roof and a stick figure labeled "BOUNCY CASTLE." "This is our intel?" Bill asked, squinting. "A five-year-old's art project?" "Timmy's cousin drew it. It's accurate. There's a bounce house, a magician, and approximately forty unsupervised presents." Bill crossed his arms. "We're robbing a birthday party." "We're liberating gifts from a system that gives one child too much stuff." "That's not liberation, Molly, that's larceny." "Semantics." He rubbed his temples. "How do we even get in? There's parents everywhere." "Simple. You're the magician." "I don't know magic." "You know card tricks." "One card trick. And it doesn't even work." "Kids won't know the difference. Disappear a coin, they'll think you're a wizard." Bill sighed. "And you?" "I'm the balloon lady. Big bag, easy exit, presents hidden inside." "Balloons don't hide presents." "They will if I'm holding forty of them and blocking your face." Bill stared at the drawing again, at the crooked bounce house and the pile of triangles meant to be gifts. "This is insane." "This is Tuesday," Molly said, grabbing her balloon bag. "Now go learn a card trick. We've got a three-year-old's birthday to rob."
created_at
"2026-07-01T07:27:18.489Z"
7/1/2026, 7:27:18 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2854
moderation_latency
(null)
generation_time
10492
tokens_prompt
77
tokens_completion
347
native_tokens_prompt
93
native_tokens_completion
485
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
0.005036
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01U7V58hHHKrHYCcZrg1gxLP"
is_byok
false
latency
2854
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-1782890838-K7hOWrGuQrRcprf36ylP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890838-zbo9sn8cZaXj1GvuBZSN"
upstream_id
"msg_01U7V58hHHKrHYCcZrg1gxLP"
total_cost
0.005036
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
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 70.53%, Deviation: 20.53%
neededClean
false
wordsTotal
207
wordsDialogue
146
49.9595%