NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09582328CBT51Y4K1HW72Z
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.9s
Cost:
$0.002062
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 Sweet Pea Bakery jingled as Nora set a tray of lemon scones on the cooling rack. Outside, Main Street gleamed after a night rain, and inside the air was warm with butter, sugar, and coffee. “Tell me you saved me one of those before the town council arrives.” Nora slid a wrapped scone across the counter. “Only because I like you better than the council.” “High praise.” A rustle came from the back room, followed by a suspicious thump. Nora frowned. “Did you hear that?” “Mice don’t usually knock.” Nora reached beneath the counter and pulled out the rolling pin her grandmother had insisted was a perfectly respectable weapon. “If it’s the same mouse that’s been stealing currants, I’m charging rent.” The back door creaked open by an inch, then wider. A gust of flour drifted out, white as fog. “That’s not a mouse.” “No, it’s not.” In the doorway stood Mrs. Bell, the town’s retired judge, clutching Nora’s antique recipe tin as if it might explode. “I may have found something in your storeroom,”
she said
. Nora took the tin, her fingers tightening on the dented lid. “Found it where?” Mrs. Bell glanced over her shoulder, then lowered her voice. “Under the flour sacks. And before you ask, no, it wasn’t there yesterday.”
created_at
"2026-03-18T10:51:42.545Z"
3/18/2026, 10:51:42 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3253
moderation_latency
(null)
generation_time
3366
tokens_prompt
81
tokens_completion
503
native_tokens_prompt
67
native_tokens_completion
447
native_tokens_completion_images
0
native_tokens_reasoning
148
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
0.00206175
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0e1d074b1f875fd90169ba83be99b481909b16ad5be36cd5df"
is_byok
false
latency
188
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-1773831102-gsh5Oo3VnnLnXj0FGbNa"
upstream_id
"resp_0e1d074b1f875fd90169ba83be99b481909b16ad5be36cd5df"
total_cost
0.00206175
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 said"