NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFKB9S6Q38WYMW2Z45HVXV1
Run Details
Model:
Stealth: Hunter Alpha
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.3s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 chimed, a familiar, tinny sound against the warm thrum of the ovens. Flour dust motes danced in a beam of late afternoon sun. “I’m telling you, it’s not right. The vanilla extract is always full on Mondays.” “A delivery hiccup, maybe. Or you used more than you thought in the Saturday scones.” “Never. I measure. And look—this is the second time this month. A whole bottle, just… gone. And the lock on the pantry hasn’t been forced.” “Hmm. You know, old Mr. Henderson said he saw a light moving back here last night. Thought it was you, doing a late bake.” “I was home by eight. And my car was in the driveway.” “So someone else has a key?” A pause, filled with the soft *thump* of dough being punched down. “The only other key is the spare. And it’s been hanging on the hook by the register since we opened.” “The one anyone could see? And take?” “…Anyone who knew where to look.”
created_at
"2026-03-11T23:22:41.33Z"
3/11/2026, 11:22:41 PM
model
"openrouter/hunter-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3018
moderation_latency
(null)
generation_time
10255
tokens_prompt
81
tokens_completion
442
native_tokens_prompt
2111
native_tokens_completion
363
native_tokens_completion_images
(null)
native_tokens_reasoning
179
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-1773271361-U7NR1ot2Izcb4BBjkXKJ"
upstream_id
"gen-1773271361-U7NR1ot2Izcb4BBjkXKJ"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)