NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AB4X2YA6A6VVVGT55YNTD
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.9s
Cost:
$0.001918
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 Maple Street Bakery gave its cheerful jingle just as the cinnamon rolls came out of the oven. Warm air rolled over the glass case, carrying butter, sugar, and a whisper of trouble. “You’re early.” “I needed a cup of coffee and a reason to pretend I wasn’t curious.” “That sounds like you.” “It sounds like this town. Everyone’s curious. You just happen to be hiding behind a tray of eclairs.” A sigh rustled through the flour-dusted back counter. “If you’re here about the missing ledger, I still don’t know anything.” “Missing ledger?” “Don’t do that.” “I didn’t say anything.” “You raised your eyebrows so high they nearly hit the fresh bread.” A laugh escaped despite itself. “Fine. I came because Mrs. Dalloway said you found something strange in the sugar.” “That was before I started locking it up.” “Then it was strange.” A pause, then the clink of a spoon against a mug. “There was a note.” “A note?” “Folded into the bag. Tiny paper, tucked between the grains like it wanted to vanish.” The bakery seemed to hush around them, the ovens humming, the register drawer waiting. “What did it say?” Another pause. “It said, ‘Check the blackberry jam before closing.’” From the front display, a jar of dark purple jam gleamed in the morning light, innocent as a Sunday school hymn.
created_at
"2026-03-18T11:12:24.493Z"
3/18/2026, 11:12:24 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4126
moderation_latency
(null)
generation_time
4337
tokens_prompt
81
tokens_completion
516
native_tokens_prompt
67
native_tokens_completion
415
native_tokens_completion_images
0
native_tokens_reasoning
115
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
0.00191775
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ad2e685cd5e950c0169ba88988f508190834def4048ba3579"
is_byok
false
latency
180
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-1773832344-LOd8veZQReAJPoH3In9w"
upstream_id
"resp_0ad2e685cd5e950c0169ba88988f508190834def4048ba3579"
total_cost
0.00191775
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)