NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAENGE2MGRW090A7BAPRDY
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.4s
Cost:
$0.003714
Provider:
OpenAI
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
“You’re late. The cinnamon rolls staged a revolt.” “They smell contrite to me. Did you burn another batch or is that just small-town gossip aflame again?” “Neither. Somebody picked the lock on the back door.” “Again? That’s the third time this month. Maybe they’re just after the secret scone recipe.” “If they were, they’re terrible at it. Nothing’s missing. Not the cash, not the pastries, not even the apricot jam with the lid welded on by Satan himself.” “Anything moved?” “The ledger. It was on the counter last night. This morning, it was tucked under the flour bags.” “That ancient blue book with the flowered cover? Maybe it just walked away in shame from your math.” “Laugh it up. The pages were warm. Like someone had been holding it. There was a smudge of chocolate on last Thursday’s entry.” “You don’t use chocolate on Thursdays.” “Exactly. And none of our regulars ordered anything chocolate yesterday.” “So someone broke in, touched nothing edible, ignored the register, and left mysterious cocoa fingerprints on your orders.” “Doesn’t that sound like a breadcrumb trail to you?” “In a bakery, everything sounds like a breadcrumb trail.” “Say it. You think I’m imagining things.” “I think someone’s using your bakery to send messages.” “Then we’d better figure out who’s reading them before they order something…deadly.”
created_at
"2026-02-16T13:32:59.234277+00:00"
2/16/2026, 1:32:59 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4274
moderation_latency
(null)
generation_time
10037
tokens_prompt
81
tokens_completion
515
native_tokens_prompt
67
native_tokens_completion
363
native_tokens_completion_images
0
native_tokens_reasoning
66
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
0.00371375
router
(null)
provider_responses
0
id
"resp_02dcce8332497ff50169931c80f7488194908777be713899de"
status
200
is_byok
false
latency
221
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248768-MUZkL6CeO7uwJjmHs4MO"
upstream_id
"resp_02dcce8332497ff50169931c80f7488194908777be713899de"
total_cost
0.00371375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)