NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA36EARXMTWC26Y8AMJ66D
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
50.3s
Cost:
$0.008566
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 folding table stacked with paper plates and a suspiciously deflated unicorn balloon, whispering like incompetent ninjas. The living room smelled of frosting and crushed crayons; a pastel war zone of streamers and discarded favor bags. They mapped snack tables and speaker placements with exaggerated gestures, eyes bright with kleptomaniac glee. Outside, a sprinkling of winter drizzle made the porch slick, amplifying their dramatic stakes. They rehearsed small talk and distraction lines, practiced pocket checks, and argued gently over whether glitter constituted a felony seriously. Molly: "We sneak in through back, cake distraction, balloons as cover." Bill: "Do we wear bunny suits or tiny tuxedos for misdirection?" Molly: "Bunny suits, obviously, pockets sewn for presents and confetti tomfoolery." Bill: "How about we bribe the magician with a valve escape?" Molly: "Timing is key; parents' attention on piƱata cues the chaos." Bill: "We stash gifts in bags labeled 'Help Santa' for comedy." Molly: "What about escape route? Sliding down a birthday banner, dramatic." Bill: "We must avoid the chatty aunt counting presents like inventory." Molly: "Sugar rush children are unpredictable; treat them like confetti grenades." Bill: "Selfie stick as pole vault for emergency rooftop exit, yes?"
created_at
"2026-02-16T13:27:23.635155+00:00"
2/16/2026, 1:27:23 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2957
moderation_latency
(null)
generation_time
50006
tokens_prompt
77
tokens_completion
1354
native_tokens_prompt
66
native_tokens_completion
4275
native_tokens_completion_images
0
native_tokens_reasoning
3968
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
0.0085665
router
(null)
provider_responses
0
id
"resp_0b8dfcd3e85472cb0169931b08b8d08193a25110dd76869ab1"
status
200
is_byok
false
latency
114
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248392-vVpqedrqPx1M8A1sf8Xq"
upstream_id
"resp_0b8dfcd3e85472cb0169931b08b8d08193a25110dd76869ab1"
total_cost
0.0085665
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
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%