NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0861VKRS2CB7XJB7Y17AWP
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2.7s
Cost:
$0.001526
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 as the morning air spilled in, carrying the smell of rain and wet brick. “Tell me again why you’re kneading dough at six-thirty in the morning instead of sleeping like a sensible person?” “Because sensible people don’t own bakeries.” “Debatable.” A tray of cinnamon rolls came out of the oven, their edges glossy with melted sugar. Behind the counter, Clara set them down and waved away the steam with her oven mitt. “If you’re here to mock my life choices, at least buy a scone.” “I came for the scone, the coffee, and the scandal.” Clara arched a brow. “We have a scandal?” “Maybe. Mrs. Pritchard’s cat was seen in the mayor’s garden last night, and now three rose bushes are missing.” “That sounds more like a gardening crime than a scandal.” “It gets better. The missing roses were found in a basket outside your back door this morning.” Clara paused, flour dusting her hands like snow. “That’s odd.” “Odd enough that Deputy Owens asked if you noticed anyone lurking around after closing.” A tiny bell inside the bakery seemed to stop ringing all at once. “Well,”
Clara said
, glancing toward the back hall, “now that is the first interesting thing all week.”
created_at
"2026-03-18T10:34:40.383Z"
3/18/2026, 10:34:40 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2333
moderation_latency
(null)
generation_time
2530
tokens_prompt
81
tokens_completion
475
native_tokens_prompt
67
native_tokens_completion
328
native_tokens_completion_images
0
native_tokens_reasoning
47
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
0.00152625
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ce8056399aaaa820169ba7fc0710c8197ac67889dc8393d62"
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-1773830080-LopWdM9K02Le95uJNW5t"
upstream_id
"resp_0ce8056399aaaa820169ba7fc0710c8197ac67889dc8393d62"
total_cost
0.00152625
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
"Clara said"