NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFBZKFNYCY26E742JRWG43S
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.9s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
0.76%
Dialogue to Total Word Ratio
(details)
30.5165%
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
Molly unrolled the blueprints across the sticky table of their favorite diner, tracing a finger along the venue layout she'd sketched from memory. "Security's tight," she said. "Three bouncy castles. Two clown guards." "Clown guards?" Bill squinted at the drawing. "You're kidding." "I wish I were. They've got those seltzer hoses." She tapped the paper. "But I've found a blind spot behind the helium tank. We go in at 2:15, right during cake time. No kid looks up from cake." Bill rubbed his hands together. "What's the score?" "Twelve wrapped boxes, minimum. I spotted a PlayStation. Two LEGO sets. Some kind of dollhouse bigger than my first apartment." "Dollhouse," Bill repeated, offended. "It's architecturally impressive. Don't judge." Molly folded her arms. "You bring the disguises?" Bill produced two party hats and a bag of candy. "We walk in like parents. Blend with the crowd. Smile at children. Act natural." "That's the part that scares me," Molly said. "Smiling at children." "You practiced in the mirror?" "For three hours." She grimaced. "I looked like a tax auditor." "That'll do," Bill said, pocketing the candy. "We're in."
created_at
"2026-03-11T21:13:58.017Z"
3/11/2026, 9:13:58 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
869
moderation_latency
(null)
generation_time
3787
tokens_prompt
77
tokens_completion
376
native_tokens_prompt
2187
native_tokens_completion
350
native_tokens_completion_images
(null)
native_tokens_reasoning
68
native_tokens_cached
2121
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-1773263638-RhLXdQryKJnlCP9ZbzRN"
upstream_id
"gen-1773263638-RhLXdQryKJnlCP9ZbzRN"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
0.76%
Dialogue to Total Word Ratio
Ratio: 64.86%, Deviation: 14.86%
neededClean
false
wordsTotal
185
wordsDialogue
120
30.5165%