NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8WV0MHBYTJNNF1Y2F2K54
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.5s
Cost:
$0.004916
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
84.30%
Dialogue to Total Word Ratio
(details)
90.9638%
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
Bill leaned against the wall, arms crossed. "So we just walk in, grab the presents, walk out. Simple." "Simple? Bill, it's a seven-year-old's birthday party. There's gonna be, like, forty screaming children and at least three moms with phones." "So?" "So they document everything! You want to end up on someone's Instagram story mid-heist?" "Nobody's gonna recognize us. We'll wear the costumes." "What costumes?" "I was thinking... clowns." "Clowns. You want us to dress as clowns to rob a birthday party." "Kids trust clowns!" "Kids are TERRIFIED of clowns, Bill, that's literally a whole cultural phenomenon." "Fine, fine. Superheroes then. Like the entertainment." "That's actually not bad. Nobody questions a hired superhero." "See? I have good ideas." "You had one good idea. What's the plan once we're inside?" "We find the present table, we bag it, we bounce." "And the parents watching their kid's party like hawks?" "We tell them we're taking the gifts backstage for the 'magic present blessing.'" "The what?" "I don't know, Molly, I'm improvising!" "There's no such thing as a magic present blessing." "There is now." "You're unbelievable." "You love it." "I tolerate it. Now go find us capes."
created_at
"2026-07-01T07:22:03.68Z"
7/1/2026, 7:22:03 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1416
moderation_latency
(null)
generation_time
8475
tokens_prompt
77
tokens_completion
342
native_tokens_prompt
93
native_tokens_completion
473
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
0.004916
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01FaaArP7kyKSgPxCcbChHL6"
is_byok
false
latency
1414
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-1782890523-v1hU80CSj6qY0NSdCCXS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890523-A7noZoiH3LIrIefH3UVc"
upstream_id
"msg_01FaaArP7kyKSgPxCcbChHL6"
total_cost
0.004916
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
97.63%
Matches word count
n/a
neededClean
false
words
193
84.30%
Dialogue to Total Word Ratio
Ratio: 96.43%, Deviation: 6.43%
neededClean
false
wordsTotal
196
wordsDialogue
189
90.9638%