NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYYXAH7RQQJTEXC03TBRF2C
Run Details
Model:
Claude Haiku 4.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.4s
Cost:
$0.001720
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
96.8209%
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
# The Birthday Bash Caper Molly adjusted her ski mask. "So we hit the Henderson residence at exactly two o'clock?" "When the piñata comes out," Bill confirmed, checking his clipboard. "That's our window." "How many presents are we talking?" "Preliminary reconnaissance suggests forty-seven wrapped boxes. Conservative estimate puts us at fifteen hundred in retail value." Molly whistled. "Those kids are loaded. What's the extraction plan?" "We go in through the side door disguised as balloon artists. You have the van parked outside?" "Idling on Maple Street. But Bill, won't someone notice two adults stuffing presents into a cargo van?" "They'll be distracted by the magician. I hired him specifically for crowd control." "Brilliant. What about the cake? Do we take that?" Bill paused. "The birthday cake? Why would we steal a cake?" "Why wouldn't we? It's carrot cake. Those things go for forty bucks." "Molly, we're thieves, not bakery bandits. Focus." "You're right, you're right. So two o'clock, side door, balloon disguises. We're really doing this?" "We're really doing this. Now, one more thing—what's our code word if things go south?" "Sprinkles," Molly said. "If anyone yells 'sprinkles,' we abort."
created_at
"2026-02-08T15:46:23.2086+00:00"
2/8/2026, 3:46:23 PM
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1214
moderation_latency
(null)
generation_time
5257
tokens_prompt
61
tokens_completion
281
native_tokens_prompt
75
native_tokens_completion
329
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
0.00172
router
(null)
provider_responses
0
id
"msg_01BHSkU8nEiJKPNsfwSGgHt5"
status
200
is_byok
false
latency
1208
endpoint_id
"41d2915a-92e6-4993-b537-210b4e10cba8"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770565577-L0erEegcxOdmrrVsuhgX"
upstream_id
"msg_01BHSkU8nEiJKPNsfwSGgHt5"
total_cost
0.00172
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
99.99%
Dialogue to Total Word Ratio
Ratio: 89.06%, Deviation: 0.94%
neededClean
false
wordsTotal
192
wordsDialogue
171
96.8209%