NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFF70BK5CG0NQ72EJVBJ2JK
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.7s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Bill flattened himself against the side of Gary Henderson's minivan, adjusting his black ski mask for the ninth time in two minutes. Through the hedge, he could see the backyard — a wasteland of pink and blue streamers, a deflating bounce house, and a table groaning under the weight of wrapped packages. "There it is," he whispered. "Christmas in June." Molly crouched beside him, her duffel bag already unzipped and ready. She studied the terrain with the intensity of a four-star general. The enemy forces — approximately fifteen six-year-olds — were currently gathered around a magician who kept pulling the same scarf from behind his ear. "How many gifts?" she asked. "Forty-two. I counted twice." "You counted wrong. There's forty-three." She pointed to a suspiciously placed box near the barbecue grill. "Amateur." Bill felt his pride sting. "What's the plan?" Molly produced a crude hand-drawn map from her back pocket. "You create a distraction. I go in through the kitchen. We meet at the slide." "What kind of distraction?" Her eyes gleamed with dangerous enthusiasm. "You're going to tell the kids there's cake in the garage." Bill winced. "They'll stampede." "Exactly."
created_at
"2026-03-11T22:10:26.307Z"
3/11/2026, 10:10:26 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
877
moderation_latency
(null)
generation_time
4595
tokens_prompt
77
tokens_completion
420
native_tokens_prompt
2147
native_tokens_completion
367
native_tokens_completion_images
(null)
native_tokens_reasoning
103
native_tokens_cached
2145
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-1773267026-wkhwmTmLdksM8M43SAkq"
upstream_id
"gen-1773267026-wkhwmTmLdksM8M43SAkq"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 29.38%, Deviation: 19.38%
neededClean
false
wordsTotal
194
wordsDialogue
57
40.6364%