NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AHB0SYJBEQC5X4G28QPPG
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.4s
Cost:
$0.002260
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 Poppy’s Bakery gave a sleepy jingle as rain ticked softly against the front window. Warm yeast and cinnamon wrapped around the room, and the glass case glowed with rows of scones, jam tarts, and glossy tea cakes. Mara set a tray of almond croissants on the counter. “You’re early.” “Only because I couldn’t stay away from your peach turnovers.” “Liar. You came for gossip.” A smile tugged at the corners of the other woman’s mouth as she slipped off her gloves. “There was an envelope tucked into the flour bin at the post office. No stamp. No name. Just a key.” Mara paused, dusting sugar from her hands. “A key to what?” “If I knew that, I wouldn’t be here.” From the kitchen came the thump of the oven door and the hiss of steam. Outside, a delivery truck rumbled past, tires whispering over wet pavement. Mara lowered her voice. “The baker’s charity auction starts tonight. Mrs. Bell expects the town council, three reporters, and one highly overconfident mayor. If that key belongs to anyone important, I’d prefer to know before the lemon meringue gets turned into a crime scene.” “Too late for that?” “Depends. Did you notice who bought the last blueberry tart?” A beat of silence. Then, “The man with the mud on his cuffs?” Mara looked toward the front door, where the rain had begun to sheet harder against the glass. “Exactly.”
created_at
"2026-03-18T11:15:47.367Z"
3/18/2026, 11:15:47 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2561
moderation_latency
(null)
generation_time
3143
tokens_prompt
81
tokens_completion
511
native_tokens_prompt
67
native_tokens_completion
491
native_tokens_completion_images
0
native_tokens_reasoning
168
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
0.00225975
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_01e07383d17d766d0169ba89636c6081968d5ad9ae1fb7877d"
is_byok
false
latency
192
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-1773832547-uaIQyH7ij9fKvdvIbOXM"
upstream_id
"resp_01e07383d17d766d0169ba89636c6081968d5ad9ae1fb7877d"
total_cost
0.00225975
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)