NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFN2YZGN1Z4Y6Z76YZ7P9CZ
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.5s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
34.0511%
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 screech of a party blower cut through the night air as Molly peered through the binoculars. "Target acquired. Bouncy castle at two o'clock, piƱata at high noon. It's a warzone, Bill." "Warzone of joy," Bill corrected, adjusting his black turtleneck. "And we're liberating the loot. Those presents won't miss themselves." "They're for *children*, Bill." "Exactly! They'll just get more. It's the circle of commerce. Now, the plan. Distraction?" Molly sighed. "You. You'll be the distraction. Blend in." Bill looked down at his all-black ensemble. "Blend in with the clowns?" "Crash the party. Act like a lost, overly enthusiastic uncle. While they're confused, I slip in, fill the sack with action figures and art kits, and we're gone before the cake is cut." "What if they ask me to do the hokey-pokey?" "Then you put your whole self in and give me thirty seconds. This isn't our first rodeo." "Our first *kiddie* rodeo," he muttered, checking the sack. "This feels morally ambiguous." "You said 'liberating the loot' sixty seconds ago." "I know. I'm having a crisis. Let's just get it done before the glitter bombs start."
created_at
"2026-03-11T23:53:05.279Z"
3/11/2026, 11:53:05 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3184
moderation_latency
(null)
generation_time
12386
tokens_prompt
77
tokens_completion
527
native_tokens_prompt
2111
native_tokens_completion
458
native_tokens_completion_images
(null)
native_tokens_reasoning
225
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-1773273185-PhrznxPMaQMobER37gld"
upstream_id
"gen-1773273185-PhrznxPMaQMobER37gld"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
0.00%
Dialogue to Total Word Ratio
Ratio: 79.79%, Deviation: 29.79%
neededClean
false
wordsTotal
188
wordsDialogue
150
34.0511%