NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AMFMDJDNRZN13V2CY426P
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2.0s
Cost:
$0.001288
Provider:
OpenAI
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 over the bakery door gave its cheerful little jingle, and warm sugar-sweet air wrapped around the room like a quilt. Behind the glass case, rows of lemon tarts, cinnamon rolls, and peach turnovers gleamed under the morning lights. “You’re late.” “By three minutes.” “Three minutes is an eternity when the scones are fresh.” A low laugh drifted from the kitchen. “You say that about every batch.” “And every batch deserves the praise.” The front window looked out onto Main Street, where a florist was setting out buckets of daisies and the hardware store next door was still half-asleep behind its dusty display. Inside the bakery, everything smelled of butter and vanilla and comfort. “You hear about Mrs. Pritchard’s missing cat?” “I heard about it from Mrs. Pritchard herself, twice, and from the cat’s portrait on the post office bulletin board.” “Then you heard she suspects the new antique dealer.” “Because he wears gloves indoors?” “Because he asked if the cat was valuable.” “Fair enough.” A tray clattered in the back. “Would you like a muffin, or are you just here to gossip?” “I came for a blueberry muffin.” “That’s what they all say.” A pause, then, softer: “And?” “And maybe for the gossip.”
created_at
"2026-03-18T11:17:30.395Z"
3/18/2026, 11:17:30 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
378
moderation_latency
(null)
generation_time
1814
tokens_prompt
81
tokens_completion
361
native_tokens_prompt
67
native_tokens_completion
275
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
0.00128775
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0246de90aec045830169ba89ca73dc8190941117e010e8710a"
is_byok
false
latency
184
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-1773832650-QytW0cxU4hoePTDB6fZb"
upstream_id
"resp_0246de90aec045830169ba89ca73dc8190941117e010e8710a"
total_cost
0.00128775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)