NC Bench
Overview
About
Tests
Models
Model
Claude Haiku 4.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZBNCM4RE1NSVC79XRSRBT
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
"So we're really doing this?" Molly whispered, adjusting her fake mustache. "Kids' birthday party at the Hilton, Saturday night. Mountains of wrapped boxes. What could go wrong?" Bill said. "Everything. We could get arrested for kidnapping adjacent crimes." "It's not kidnapping if we don't take the kids." "We're stealing their presents, Bill. That's basically emotional kidnapping." "Is it though? Think about it. These are rich kids. They'll get more presents next week." "That's not how morality works." "Look, we've robbed banks, art galleries, a minor league baseball stadium—" "We needed the copper wiring!" "—and you're drawing the line at a children's party?" Molly sighed. "When you say it like that, I sound insane." "You're not insane. You're brilliant. We'll dress as party entertainers. They'll never suspect us." "I don't know how to entertain children." "Just make balloon animals and steal stuff." "That's your entire plan? Balloon animals as a cover for grand larceny?" "Works every time." "We've never done this before!" "Exactly. They won't see it coming." Bill grinned. "Besides, what's the worst that could happen?" Molly stared at him. "Don't say that. Never say that."
created_at
"2026-02-08T15:54:12.190634+00:00"
Sunday, February 8th, 2026 at 3:54:12 PM GMT+00:00
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1045
moderation_latency
175
generation_time
4328
tokens_prompt
61
tokens_completion
274
native_tokens_prompt
75
native_tokens_completion
325
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
0.0017
router
(null)
provider_responses
0
id
"494b17e9-f328-4917-b0b6-e5ad8fc0e396"
status
200
is_byok
false
latency
1045
endpoint_id
"d000261c-5aeb-47d1-ac87-ad64dbe1cdb6"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770566047-ccmj27bt6ZzyHrmtJn6h"
upstream_id
"494b17e9-f328-4917-b0b6-e5ad8fc0e396"
total_cost
0.0017
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
187
98.7200%
Dialogue to Total Word Ratio
Ratio: 86.63%, Deviation: 3.37%
neededClean
false
wordsTotal
187
wordsDialogue
162
86.9378%