NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFFYBWYRV5G70NDM58S83ZR
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.3s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
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
The surveillance van smelled of stale coffee and clown noses. Molly traced a finger over the blueprint of the community center. “Alright, Bill. The Sugarplum Fairy’s Fourth Birthday Bash. Presents pile is in the ‘Enchanted Forest’ corner, behind the glitter volcano.” Bill adjusted his fake mustache. “Right. My role is still the overly enthusiastic magician who distracts with a truly awful rabbit trick?” “Precisely. I slip in as the face-painting auntie. Once you’ve got every parent and child horrified by your ‘levitating’ hamster, I move.” “What’s the signal?” Bill asked. “When I start painting a tiger, you yell, ‘Great Scott, the rabbit’s eaten the hamster!’ That’s chaos prime. I’ll have two minutes.” “And if the real magician shows up?” Molly sighed. “You pull the emergency glitter bomb. No one can see or breathe through that. We exit via the bounce house emergency zipper.” Bill patted his pocket. “I’ve got the whoopee cushions for the exits. Non-lethal, but deeply demoralizing.” “Perfect. Remember: we’re not monsters. We leave the fruit cups and the one gift card to the petting zoo.” “Professional courtesy.” Bill nodded solemnly. Molly grinned. “Now, let’s go steal some LEGOs.”
created_at
"2026-03-11T22:23:11.786Z"
3/11/2026, 10:23:11 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1911
moderation_latency
(null)
generation_time
11250
tokens_prompt
77
tokens_completion
577
native_tokens_prompt
2111
native_tokens_completion
476
native_tokens_completion_images
(null)
native_tokens_reasoning
230
native_tokens_cached
1984
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-1773267791-wCzy3bLn9UjxpKkQwOML"
upstream_id
"gen-1773267791-wCzy3bLn9UjxpKkQwOML"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
0.00%
Dialogue to Total Word Ratio
Ratio: 79.79%, Deviation: 29.79%
neededClean
false
wordsTotal
193
wordsDialogue
154
46.8248%