NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFBZ80EC2YVN1WRA71BT4HC
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.1s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
0.49%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
50.2460%
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
“Look at this invitation. ‘Princess Pops’ sixth birthday. There will be a piñata. A glorious, candy-filled piñata.” Molly tapped the glittery card. “It’s our duty.” Bill peered from behind the curtain. “Molly, it’s a backyard party. There are tiny humans. They’re armed with noisemakers.” “Precisely. They’re distracted. We move in during the cake-induced sugar crash. You create a diversion.” “A diversion? What kind? I’m not doing the chicken dance again.” “No. You will start a conga line. A long, winding, irresistible conga line. It will funnel them away from the gift table.” “And you?” “I will be the shadow, the breeze, the silent liberator of presents. I’ve studied the list. There are at least three LEGO sets. Unopened.” “What if a kid sees you?” “You offer them a slice of rainbow cake. From their own kitchen. It’s the perfect crime.” Bill sighed, glancing at the backyard. “Fine. But if a clown shows up, I’m out. I draw the line at clowns.” “Noted. Now, review the conga line steps. And try to look fun.”
created_at
"2026-03-11T21:13:46.267Z"
3/11/2026, 9:13:46 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1319
moderation_latency
(null)
generation_time
9996
tokens_prompt
77
tokens_completion
533
native_tokens_prompt
2111
native_tokens_completion
441
native_tokens_completion_images
(null)
native_tokens_reasoning
233
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-1773263626-N6dev2m3k3IJ4hh57auX"
upstream_id
"gen-1773263626-N6dev2m3k3IJ4hh57auX"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
0.49%
Matches word count
n/a
neededClean
false
words
173
100.00%
Dialogue to Total Word Ratio
Ratio: 90.29%, Deviation: 0.29%
neededClean
false
wordsTotal
175
wordsDialogue
158
50.2460%