NC Bench
Overview
About
Tests
Models
Model
Claude Sonnet 4.5
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYX0MGY2BSFTK6XXK14PD5W
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 squinted through the binoculars at the bounce house. "Twenty kids, maybe thirty. All hopped up on cake." "That's a lot of witnesses," Bill said, adjusting his fake mustache nervously. "They're six years old. Who's gonna believe them?" Molly lowered the binoculars. "Besides, we need this score. Rent's due." "I still think robbing a birthday party is a new low." "Did you see the present table? That's easily two grand in LOL dolls and Lego sets alone." Bill sighed. "What's the plan?" "You go in as the clown. I already got you the costume." "I'm not being a clown again, Molly. Last time I got kicked in the shins seventeen times." "Fine. Then you're the pony." "The what?" Molly pointed to a sad-looking pony tied near the fence. "We swap you in. Nobody notices. When the piƱata breaks, everyone rushes for candy. That's when I grab the presents." "How exactly do I impersonate a pony?" "I don't know, Bill. Eat some grass. Look horsey." She handed him a ski mask with ears sewn on. "Now stop whining and get into character."
created_at
"2026-02-08T15:13:17.606899+00:00"
Sunday, February 8th, 2026 at 3:13:17 PM GMT+00:00
model
"anthropic/claude-4.5-sonnet-20250929"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1675
moderation_latency
138
generation_time
8408
tokens_prompt
61
tokens_completion
254
native_tokens_prompt
75
native_tokens_completion
304
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.004785
router
(null)
provider_responses
0
id
"2b990f30-6cff-41bd-b0d7-f81818b19da1"
status
200
is_byok
false
latency
1675
endpoint_id
"d8bee848-f020-454a-b2be-4a7ce868f99f"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-sonnet-20250929"
api_type
"completions"
id
"gen-1770563588-WrKtzhtH8y9hdW83I7kb"
upstream_id
"2b990f30-6cff-41bd-b0d7-f81818b19da1"
total_cost
0.004785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
0.0000%
Dialogue to Total Word Ratio
Ratio: 76.37%, Deviation: 26.37%
neededClean
false
wordsTotal
182
wordsDialogue
139
17.5011%