NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB4FH2Q0ASZW1NP9R3XMBY
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 23s
Cost:
$0.007409
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly: Are you sure about this? It's a children's party. Bill: Positive. Presents are glorious and we are professionals. Molly: We promised Grandma we'd stop taking things. Bill: Promises are like balloons; they drift away. Molly: Fine. What's the plan? Bill: I wear the costume and create a diversion. You sneak in, gather the gifts, we leave unnoticed. Molly: Your costume better be convincing. Bill: It's terrifyingly convincing. Banana logic never fails. Molly: If you dance, children will cry. Bill: That's the point. Crying scatters cake. We act like concerned caterers and gather presents for safe keeping. Molly: I'm in. Night shimmered through the window as party songs muffled into the hallway. Molly tightened a suspiciously small bow tie and felt ridiculous and electric. Bill rehearsed a moonwalk that looked more like a confused penguin, grinning as he imagined mountains of ribbon and glitter. Their plan was a whisper, more hope than map; it relied on bad timing, better acting, and enormous audacity. They practiced sympathetic frowns and practiced not crying when confronted by tiny scowls. Somewhere inside the house, a piƱata waited like a secret. They were thieves with hearts too soft for guilt but perfectly flexible for mischief.
created_at
"2026-02-16T13:46:06.47921+00:00"
2/16/2026, 1:46:06 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
20718
moderation_latency
(null)
generation_time
82275
tokens_prompt
77
tokens_completion
1447
native_tokens_prompt
66
native_tokens_completion
3696
native_tokens_completion_images
0
native_tokens_reasoning
3392
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
0.0074085
router
(null)
provider_responses
0
id
"resp_0a67dba7ac8377d50169931f4b63088197b6ee6fb18acc3c26"
status
200
is_byok
false
latency
145
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249483-VAS8ukbJutakhHVtB0I1"
upstream_id
"resp_0a67dba7ac8377d50169931f4b63088197b6ee6fb18acc3c26"
total_cost
0.0074085
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
50.0000%