NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9DMWX3Z2G2Q7ZEVQ80J4F
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
12.3s
Cost:
$0.001997
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 sure you found it inside the tart, not stuck to the box?” “Positive. It was folded like a tiny map, butter-smell and all.” “A map to what? The back door? The old mill? Please don’t say the mayor’s azaleas.” “It’s not directions. It says, ‘Stop the rehearsal or the oven will sing.’” “You’re joking.” “I’m not. And before you ask, yes, I checked the sugar — no glitter, no ink but that smudge.” “If someone wanted to scare you, there are easier ways than poetry and pastry.” “Maybe they wanted to be dramatic. Or maybe someone wanted me to stop baking the Blueberry Glory.” “You retired that recipe when Mrs. Hargrove returned from Florida.” “She didn’t return the recipe card. She gave me tea and a smile and ten days later, my scones went viral.” “Small towns have long memories and longer grudges. Did you lock the recipe drawer?” “Locked, bolted, blessed. Still, something smells off besides lemon zest.” “Maybe ask the delivery boy about the flour sacks. Or the florist who’s been buying your leftover baguettes.” “Or the person who knows how to fold a note and hide it in a tart.” “Then we start with everyone who thinks a recipe is worth more than a neighbor.”
created_at
"2026-02-16T13:14:59.575415+00:00"
2/16/2026, 1:14:59 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6146
moderation_latency
(null)
generation_time
11960
tokens_prompt
81
tokens_completion
641
native_tokens_prompt
67
native_tokens_completion
990
native_tokens_completion_images
0
native_tokens_reasoning
704
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
0.00199675
router
(null)
provider_responses
0
id
"resp_068a9c1d41fb97ca0169931846a72c8193b2d190716345e56c"
status
200
is_byok
false
latency
139
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771247686-Vnl8jeeJrUVJ2T7gCjQh"
upstream_id
"resp_068a9c1d41fb97ca0169931846a72c8193b2d190716345e56c"
total_cost
0.00199675
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)