NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA7EDRSKTMY80Y6698HNAQ
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.5s
Cost:
$0.001805
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 baked these earlier than usual; the lemon drizzle is still dewy. Someone left the back door unlocked again and the oven timer did a midnight duet with the wind. That explains the flour footprints on the stoop—wide, hurried, like someone carrying secrets and a sack of sugar. Secrets don't rise like bread. They fester under the display glass until someone asks the right question. Did you see the note tucked under the jam tarts? “For emergencies only,”
in Mrs
. Pritchard's looping hand. I saw it. I saw the smear on the note that matches the purple scarf you always borrow. You think she left it on purpose? Mrs. Pritchard never leaves things to chance, only to recipes. Recipes and remembrances, remember? She called this morning, voice too steady. Asked about the walnut loaf and whether anyone else knew the proportion of honey to crust. Why honey? She never used honey. Ever. Maybe someone wanted the old honey measure back in her ledger. Maybe someone wanted the bakery's backroom key. Maybe someone wanted the ledger for a recipe, and found something else instead. Like a ledger entry that doesn't belong to baking. Like a name you don't want in your buttercream.
created_at
"2026-02-16T13:29:03.006365+00:00"
2/16/2026, 1:29:03 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8081
moderation_latency
(null)
generation_time
10164
tokens_prompt
81
tokens_completion
317
native_tokens_prompt
67
native_tokens_completion
894
native_tokens_completion_images
0
native_tokens_reasoning
576
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
0.00180475
router
(null)
provider_responses
0
id
"resp_0b7ee92d93f55c790169931b940ecc8193816a5f67f7190e8e"
status
200
is_byok
false
latency
155
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248531-AFpJ4s5URVHaUjRwQeiW"
upstream_id
"resp_0b7ee92d93f55c790169931b940ecc8193816a5f67f7190e8e"
total_cost
0.00180475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
60.6531%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"in Mrs"