NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFEVAN24E5X0R753Y5JXCV0
Run Details
Model:
Stealth: Healer Alpha
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.8s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
13.53%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door jingled, announcing the morning’s first customer. “Fresh scones are still cooling, but the cinnamon rolls just came out of the oven.” “You’re a lifesaver. I had a feeling I’d need something warm today.” “Everything alright, Henry? You look a bit… thoughtful.” “It’s about the old mill. Found something in the records that doesn’t quite fit.” “Oh?” “A ledger entry from the day before the fire. A delivery that was never logged.” “That’s odd. Everything was so meticulously documented back then.” “It is odd. Especially since the delivery was from your great-uncle’s farm.” “…My great-uncle sold dairy, not lumber or bricks.” “Exactly. So what was in that delivery, Martha?” A long pause, filled only with the hum of the refrigerator and the scent of yeast. “The recipe,”
she whispered
, turning to arrange a tray of pastries that didn’t need arranging. “He brought a basket of eggs. But there was something else tucked underneath. A pressed flower. A single, black orchid.” “And you think that’s connected to why the mill burned down?” “I think,”
she said
, finally meeting his eyes, “that someone was trying to send a message. And I think that message has finally been found.”
created_at
"2026-03-11T22:04:03.632Z"
3/11/2026, 10:04:03 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
817
moderation_latency
(null)
generation_time
5672
tokens_prompt
81
tokens_completion
618
native_tokens_prompt
2147
native_tokens_completion
502
native_tokens_completion_images
(null)
native_tokens_reasoning
262
native_tokens_cached
2080
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-1773266643-7gDNZ7fbcwwgaNI5QfN5"
upstream_id
"gen-1773266643-7gDNZ7fbcwwgaNI5QfN5"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she whispered"
1
"she said"