NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAAGC5E42DAPNV9JF4E7W1
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 16s
Cost:
$0.039192
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
Confetti gusted across the parking lot as Molly and Bill crouched behind a lopsided bouncy castle shaped like a dragon. Their getaway scooter purred, disguised beneath a heroic rainbow blanket. A chorus of toddlers howled inside, sugar-fueled and formidable. Balloons bobbed like surveillance jellyfish, judging everything. Bill adjusted his paper crown; Molly checked a stopwatch shaped like a cupcake. They had studied the terrain: cake table, present mountain, and a magician who looked suspiciously competent. The air smelled of frosting, fear, and faint citrus cleaner. Somewhere, a piƱata creaked, plotting louder than either thief. Timing, flair, and birthday spirit ruled. "Molly: Remember, we mingle, compliment the cake, then wheel the present mountain onto our scooter. If asked, we're emergency gift auditors with excellent ribbons, credentials." "Bill: Auditing toddlers seems dangerous; they file grievances in frosting. Distraction plan B: kazoo solo, followed by interpretive balloon whispering. No one suspects inventory work." "Molly: Excellent. If the magician interferes, I'll shout abracadabra at his mustache and produce a legally binding glitter cloud. You nod gravely and stamp forms." "Bill: And if cake becomes hostile, we deploy napkins diplomatically, accept surrender sprinkles, and vanish behind the dragon. Remember, presents prefer thieves with nap-friendly shoes."
created_at
"2026-02-16T13:31:48.297122+00:00"
2/16/2026, 1:31:48 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14949
moderation_latency
(null)
generation_time
75649
tokens_prompt
77
tokens_completion
1747
native_tokens_prompt
66
native_tokens_completion
3911
native_tokens_completion_images
0
native_tokens_reasoning
3584
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
0.0391925
router
(null)
provider_responses
0
id
"resp_0cef43ed27721bdc0169931bf8be24819483702770de237a96"
status
200
is_byok
false
latency
453
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771248632-0irRmYhjfwoDbZXdPTpu"
upstream_id
"resp_0cef43ed27721bdc0169931bf8be24819483702770de237a96"
total_cost
0.0391925
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
202
wordsDialogue
101
99.9920%