NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFKTMQQ84KZTHPQF7GZDWED
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.7s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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 minivan idled down the street from the bouncy castle. Inside, Molly adjusted her cat-ear headband, glaring at the glittery invitation on the dashboard. “It’s a piñata, Bill. A giant donkey full of gummy bears. This isn’t the Met Gala.” “Precisely!” Bill whispered, wrestling with his oversized bow tie. “No lasers. Just one security guard—napping, probably. In and out. Think of the loot: twenty-three present-wrapped boxes, a mountain of snack-size chips, and that piñata. It’s the soft target of the century.” “Soft target, hard floor.” Molly pointed. “That’s the birthday kid’s dad. He looks like he benches minivans.” “A minor complication.” Bill slid on sunglasses. “Phase One: Distraction. You create a diversion at the snack table.” “What kind of diversion?” “The ‘Oops, I spilled the juice’ kind. Classic. While everyone’s slipping, I make the grab.” “You’ll be grabbing a juice box.” Molly sighed, but a smile crept in. “Fine. But if we get taken down by a clown named Bubbles, I’m leaving you to the mob of five-year-olds.” “Deal. Now, remember the code word. When I say ‘sparkle,’ we run.” “Sparkle,” Molly muttered, shaking her head. “This is going to be a disaster.”
created_at
"2026-03-11T23:31:04.069Z"
3/11/2026, 11:31:04 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1150
moderation_latency
(null)
generation_time
10642
tokens_prompt
77
tokens_completion
571
native_tokens_prompt
2111
native_tokens_completion
480
native_tokens_completion_images
(null)
native_tokens_reasoning
227
native_tokens_cached
2048
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-1773271864-WUvInRL4ER1lIknahCXC"
upstream_id
"gen-1773271864-WUvInRL4ER1lIknahCXC"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
0.00%
Dialogue to Total Word Ratio
Ratio: 74.50%, Deviation: 24.50%
neededClean
false
wordsTotal
200
wordsDialogue
149
49.3562%