NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFJAJ6K4DVN3VAGWF34VKSY
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.2s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.8117%
Overall
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 unfurled the blueprint across the wobbly kitchen table, scattering crumbs from a croissant. “The target is a birthday party. ‘Sir Knight’ theme. The presents are under a plastic castle.” Bill leaned in, squinting. “A heist? At a party for five-year-olds? The security will be brutal.” “The security is a grandmother who’s had two glasses of prosecco,” Molly said, pointing to a blurry photograph. “Her name is Glenda. We go in at peak sugar-rush, around 3:30 PM. Distraction is key.” “Got it. I’ll create a diversion. I’ll… do a really bad magic trick. Make a rabbit disappear. From a hat. That I don’t have.” “Bill. No.” Molly sighed, tapping the image of a pile wrapped in neon paper. “You’ll pose as the ‘Fun-Time Balloon Animal Technician.’ You inflate, you twist, you get the kids’ attention. I’ll slip in through the patio, grab the loot sack, and exit via the pet door.” “What’s the loot?” “Mainly. And a suspiciously large number of ‘Poopsie Slime Surprise’ things.” “They’re for Glenda’s collection. She’s got a fever for the slime.”
created_at
"2026-03-11T23:04:48.608Z"
3/11/2026, 11:04:48 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
497
moderation_latency
(null)
generation_time
4078
tokens_prompt
77
tokens_completion
531
native_tokens_prompt
2147
native_tokens_completion
479
native_tokens_completion_images
(null)
native_tokens_reasoning
228
native_tokens_cached
2081
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
router
(null)
provider_responses
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773270288-qoNGYYdYIYFyRnHba1WC"
upstream_id
"gen-1773270288-qoNGYYdYIYFyRnHba1WC"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
3.62%
Matches word count
n/a
neededClean
false
words
176
0.00%
Dialogue to Total Word Ratio
Ratio: 79.33%, Deviation: 29.33%
neededClean
false
wordsTotal
179
wordsDialogue
142
1.8117%