NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFM91JEBC39EZB7YZHQXHBD
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.0s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
25.9628%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprint was spread across the sticky diner table, its creases filled with coffee rings and a stray sprinkle. Molly, her finger tracing a dotted line, pointed. "The vent access is here, above the ball pit." Bill leaned in, his mustache twitching. "Sounds lousy." She ignored him. "The target presents are clustered by the 'Princess Castle' facade. We’re in at 2:15 AM, during the scheduled ice cream truck distraction." Bill frowned. "Why do we need a distraction? It's just a bouncy house." Molly looked up, her eyes flat. "Bill. This is a professional operation. We don't cut corners on a distraction." She slid a schematic of the laser-tag arena toward him. "You handle the motion sensors. I'll neutralize the animatronic guard dog." Bill sighed, poking the drawing. "It barks 'Happy Birthday' when you step on the squeaky tile." Molly folded the blueprint with a crisp snap. "Then don't step on the squeaky tile. The loot is in those gift bags. We're talking premium plastic trinkets, Bill. The kind with the batteries pre-installed." A slow grin spread across Bill's face. "Now you're speaking my language."
created_at
"2026-03-11T23:38:55.962Z"
3/11/2026, 11:38:55 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
897
moderation_latency
(null)
generation_time
4647
tokens_prompt
77
tokens_completion
554
native_tokens_prompt
2147
native_tokens_completion
493
native_tokens_completion_images
(null)
native_tokens_reasoning
274
native_tokens_cached
2145
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-1773272336-d63qYKKYFYjgOU3B2JNu"
upstream_id
"gen-1773272336-d63qYKKYFYjgOU3B2JNu"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
0.00%
Dialogue to Total Word Ratio
Ratio: 59.46%, Deviation: 49.46%
neededClean
false
wordsTotal
185
wordsDialogue
110
25.9628%