NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9NYGCX9KMFVYJ4GMV68MS
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
38.1s
Cost:
$0.006980
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 and Bill crouched behind a hedge outside a house lit with fairy lights and the laughter of children. They checked masks, practiced silent hand signals, and compared notes on routes and parking. Molly adjusted a grappling hook while Bill consulted a floor plan drawn in crayon. The smell of frosting and hot cocoa drifted through an open window. Party music thumped. A pile of wrapped boxes caught moonlight through curtains. Neither could resist grinning at the prize list. They synchronized watches, swallowed nerves, and crept toward a side gate like burglars in a storybook. Night air tasted of opportunity. "Molly: Are you ready to steal birthday history and swap it for silence?" "Bill: Ready if you promise no glitter grenades and no singing alarms." "Molly: I'll disable the playlist and distract the hostess with a magic trick." "Bill: Your magic trick better involve disappearing with piles of presents, not confetti." "Molly: We move fast, like well-trained raccoons with a taste for wrapped toys." "Bill: Raccoons don't wear masks, Molly." "Molly: Tonight they do. Now, on three." "Bill: One, two, three." "Molly: And remember, no leaving Santa's cookies behind, Bill." "Bill: I'll carry the loot, you carry the alibi, agreed?"
created_at
"2026-02-16T13:19:57.333485+00:00"
2/16/2026, 1:19:57 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2035
moderation_latency
(null)
generation_time
37919
tokens_prompt
77
tokens_completion
1441
native_tokens_prompt
66
native_tokens_completion
3482
native_tokens_completion_images
0
native_tokens_reasoning
3200
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
0.0069805
router
(null)
provider_responses
0
id
"resp_04d4f98dbeba32d40169931956a1888197a949d1e8da01343d"
status
200
is_byok
false
latency
161
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771247958-a3FpcYuzZz2QGhCMlseb"
upstream_id
"resp_04d4f98dbeba32d40169931956a1888197a949d1e8da01343d"
total_cost
0.0069805
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
99.9995%