NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HQB67GJ68D74H61AVR44D
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.5s
Cost:
$0.004908
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 polite little jingle as warm cinnamon air wrapped around the room. Morning light pooled across the glass case, catching on apricot danishes, sugared buns, and a neat row of lavender shortbread. “You’re early.” “So are you, which makes this feel less like coincidence and more like stalking.” “If I were stalking you, I’d have chosen a place with worse coffee.” “The coffee is excellent. It’s your opinions that are bitter.” A laugh slipped between them. Behind the counter, bread cooled on racks with tiny crackling sighs. “You bought the last honey cruller.” “I bought two, actually. I simply wasn’t advertising it.” “How selfish.” “How prepared.” A paper bag was nudged across the counter. The faint dark smear on one corner did not look like chocolate. “You found it there?” “Tucked under the mixer. Folded twice.” “And no one else saw?” “Not unless Mrs. Weller has suddenly developed a talent for minding her own business.” The bag opened with a careful rustle. Inside, beneath the second cruller, lay a flour-dusted recipe card. “That’s Edith’s handwriting.” “That’s what worries me.” “Because she’s been dead ten years?” “Because the card says the same thing the note in the church raffle basket did.” A pause. Outside, a truck rumbled past. “Read it again.” “Meet me before dawn. Come alone.” “In a bakery full of gossips, that’s practically a confession.”
created_at
"2026-03-06T12:24:56.783Z"
3/6/2026, 12:24:56 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
437
moderation_latency
(null)
generation_time
10471
tokens_prompt
81
tokens_completion
426
native_tokens_prompt
67
native_tokens_completion
316
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
0.0049075
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0c9200dba77a55ea0169aac798da2c8196a21cadd035ad41c9"
is_byok
false
latency
167
model_permaslug
"openai/gpt-5.4-20260305"
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-1772799896-8PtQtYTe5PWgP5V9QDvh"
upstream_id
"resp_0c9200dba77a55ea0169aac798da2c8196a21cadd035ad41c9"
total_cost
0.0049075
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)