NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A79035D7MK0WETYP0T54K
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2.1s
Cost:
$0.001423
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.65%
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 over the bakery door gave a cheerful jingle, and warm air wrapped around Mara as soon as she stepped inside. Cinnamon, butter, and fresh bread made the whole place feel like a hug. “You’re late.” “Only by three minutes.” “Three minutes is enough to ruin a batch.” Mara laughed and tucked her scarf into her coat pocket. “If your batch is so fragile, maybe it needs a stronger baker.” “Watch it. These scones are holding this town together.” Behind the counter, trays of golden pastries cooled beneath a lattice of sunlight. Mr. Bell, flour dusting his eyebrows, slid a cherry tart into a box and glared with theatrical severity. “You didn’t hear the news?” “What news?” “The mayor’s missing his breakfast meeting.” Mara blinked. “Missing?” “Apparently.” He lowered his voice, though the bakery was empty except for an elderly woman selecting rye loaves. “He was supposed to meet the council at eight. Never showed.” “That doesn’t sound like a crime.” “No, but he also left his hat on my counter.” “So?” “So he never forgets his hat.” Mara glanced at the navy felt hat resting beside the register. Something about it sat wrong in the warm, ordinary morning. “You’re thinking what I’m thinking?”
she asked
. “I’m thinking my apple turnovers are going to go cold if we don’t solve this quickly.” “And I’m thinking you’re impossible.” “Only before coffee.”
created_at
"2026-03-18T11:10:17.618Z"
3/18/2026, 11:10:17 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
414
moderation_latency
(null)
generation_time
1923
tokens_prompt
81
tokens_completion
411
native_tokens_prompt
67
native_tokens_completion
305
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
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
"completed"
usage
0.00142275
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_083af5f142a29c970169ba8819b2408195b2df74c7aff72f1a"
is_byok
false
latency
224
model_permaslug
"openai/gpt-5.4-mini-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773832217-aDZBnP5Dzjukh4Wjg7cc"
upstream_id
"resp_083af5f142a29c970169ba8819b2408195b2df74c7aff72f1a"
total_cost
0.00142275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she asked"