NC Bench
Overview
About
Tests
Models
Model
Claude Haiku 4.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZ5M0WZM7CBDQNSZF3F7H7
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
Molly adjusted her fake mustache. "So we're really doing this? Breaking into a six-year-old's birthday party?" "The presents are top-tier this year," Bill whispered, unrolling blueprints of the gymnasium. "Three Nintendo Switches, a hoverboard, and apparently a real pony." "A pony? How does a pony fit in a gymnasium?" "Beats me, but we're taking it." "Bill, we can't steal a pony. It'll scream or bite us or something." "Fine, leave the pony. But those Switches are ours." Molly tapped the blueprints. "What's your entry strategy? The front door?" "Amateur hour. I'm going through the bounce house. Security never watches the bounce house." "That's because nobody expects criminals in a bounce house." "Exactly. It's the perfect cover. You distract the parents with the piñata situation." "What piñata situation?" "The one you're creating. Go knock it off the rope, start a chaos chain reaction." Molly groaned. "I'm a professional art thief, and I'm sabotaging children's party equipment." "Hey, we all have our moments," Bill said, grinning. "Besides, the pony might actually help us escape." "We're not taking the pony!"
created_at
"2026-02-08T15:50:53.750016+00:00"
Sunday, February 8th, 2026 at 3:50:53 PM GMT+00:00
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
566
moderation_latency
203
generation_time
3841
tokens_prompt
61
tokens_completion
270
native_tokens_prompt
75
native_tokens_completion
315
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
0.00165
router
(null)
provider_responses
0
id
"b2c7f908-6c95-4e2a-8569-88a0998ae502"
status
200
is_byok
false
latency
565
endpoint_id
"d000261c-5aeb-47d1-ac87-ad64dbe1cdb6"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770565849-TgoolTyi2oibfQl3AZ1N"
upstream_id
"b2c7f908-6c95-4e2a-8569-88a0998ae502"
total_cost
0.00165
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
20.1897%
Matches word count
n/a
neededClean
false
words
180
99.9229%
Dialogue to Total Word Ratio
Ratio: 88.33%, Deviation: 1.67%
neededClean
false
wordsTotal
180
wordsDialogue
159
60.0563%