NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE98TM6V1N9TYFNJBKBKX4Q
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.2s
Cost:
$0.004976
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
50.45%
Dialogue to Total Word Ratio
(details)
59.2745%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Say it again," Molly said. "Slower this time, because I don't think I heard you right." "We hit the party. We take the presents. We leave." "It's a six-year-old's birthday party, Bill." "So? Six-year-olds don't need a PlayStation. What's a six-year-old gonna do, review my Yelp page?" "There's gonna be, like, forty parents there." "Forty parents watching a magician pull scarves out of his sleeve. Nobody's watching the gift table, Molly. Nobody ever watches the gift table." "You want us to dress as clowns again." "I want us to dress as the *catering staff*. Big difference. Clowns, everybody remembers a clown. Catering staff, invisible. You ever remember the guy who refilled your punch bowl?" "I remember the guy who refilled my punch bowl at Denny's wedding. He stole the cake topper." "That was me." "I know it was you, Bill." "Okay, fine, bad example, but the principle stands." "And when the birthday kid starts crying because Grandma's necklace-shaped present is gone?" "We leave the necklace. We're not monsters, Molly. We take the Legos, the drones, the two hundred dollar sneakers some auntie definitely overspent on. Rich people problems." "You've really thought this through." "I think about children's parties more than a grown man should." "That's the most honest thing you've ever said to me."
created_at
"2026-07-01T07:28:36.497Z"
7/1/2026, 7:28:36 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1690
moderation_latency
(null)
generation_time
9190
tokens_prompt
77
tokens_completion
357
native_tokens_prompt
93
native_tokens_completion
479
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
0.004976
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01KXyyQcRuBmtFag89BAUmhm"
is_byok
false
latency
1690
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-1782890916-rLs8Szuhcuxq763uL1wa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890916-79qGKRhMDYYgjCisTQFD"
upstream_id
"msg_01KXyyQcRuBmtFag89BAUmhm"
total_cost
0.004976
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
68.10%
Matches word count
n/a
neededClean
false
words
214
50.45%
Dialogue to Total Word Ratio
Ratio: 99.10%, Deviation: 9.10%
neededClean
false
wordsTotal
221
wordsDialogue
219
59.2745%