NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFEP713XMV552MYTRBAXY66
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 13s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
86.37%
Dialogue to Total Word Ratio
(details)
43.1874%
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
Molly and Bill hid in the alley, masks up. "Bill, the party's in there. We need those presents." "Molly, they're kids. Have you no heart?" "My heart is made of dollar signs. Now, plan: during the song, we sneak in." "What song?" "Happy Birthday. It's long and loud." "I can't sing." "You don't have to. Just grab the sack and run." "What if a kid sees me?" "Tell them you're Santa's helper." "It's July." "Santa has a summer job." "Right. And the clown?" "The clown is on break. I checked." "You scouted a children's party?" "I'm thorough. Now, ready?" "Wait, I need to use the bathroom." "No bathrooms. Hold it. This is heisting." "Fine. But if I pee in the suit, it's on you." "Noted. Exit through the fence to the park." "Park has kids." "Different kids. Won't notice." "Unless observant." "Distracted by squirrels." "I like squirrels." "No squirrels. Ready? Go!" "Wait, what if we get caught by the parents?" "We tell them we're from the 'Toy Relocation Service.'" "That's not a thing." "To five-year-olds, it is. They have no concept of reality." "Alright. Let's do this. For the sake of heisting." "And remember, no leaving fingerprints. We use gloves." "I brought latex gloves. And a sack for the loot." "Good. Now, synchronize watches. Go at the count of three." "Wait, my watch is digital. It doesn't tick." "Just count silently. One, two, three!"
created_at
"2026-03-11T22:01:16.082Z"
3/11/2026, 10:01:16 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
497
moderation_latency
(null)
generation_time
73167
tokens_prompt
77
tokens_completion
10626
native_tokens_prompt
2147
native_tokens_completion
11922
native_tokens_completion_images
(null)
native_tokens_reasoning
10225
native_tokens_cached
2078
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-1773266476-skdFguTIXcpBxoKsNhKD"
upstream_id
"gen-1773266476-skdFguTIXcpBxoKsNhKD"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
234
86.37%
Dialogue to Total Word Ratio
Ratio: 96.19%, Deviation: 6.19%
neededClean
false
wordsTotal
236
wordsDialogue
227
43.1874%