NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAWQJ8CJD9EVP91ME5M75Z
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 9s
Cost:
$0.047582
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
In the rented storage unit, confetti drifted like dust motivated by mischief. Molly spread blueprints that were actually placemats from a pirate-themed diner. Bill balanced on a folding chair, practicing a bow grand enough to distract an auditorium of toddlers. A balloon pump wheezed heroic music; a rubber chicken stared, complicit. They rehearsed smiles calibrated to aunt-proof sincerity. He circled a stick figure cake with a crayon, she drew a wagon wearing a monocle. The plan, if it could be called that, relied on charisma, coincidence, and cupcakes. Even footprints would be festive. Distant kazooing promised opportunity or foreshadowed doom. "Molly, we need a plan with panache, not prison laundry." "Bill prefers panache, but also prefers walking away convincingly innocent." "Children's parties are fortresses of frosting; morale melts under sprinkles." "Right, we infiltrate as entertainment, dignified magicians with inflatable dignity." "My act: vanish cupcakes; your act: produce decoys from nowhere." "Decoys wrapped in thunderous paper, distracting parents into applause reflex." "Meanwhile, we wheel the real treasure aboard our noble wagon." "Noble wagon squeaks like a confession; we need stealthy glitter." "Glitter is stealthy; witnesses sparkle, forget why they're smiling anyway." "Contingency: if pinata riots erupt, we blame the hired giraffe."
created_at
"2026-02-16T13:41:39.75863+00:00"
2/16/2026, 1:41:39 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17919
moderation_latency
(null)
generation_time
69089
tokens_prompt
77
tokens_completion
1433
native_tokens_prompt
66
native_tokens_completion
4750
native_tokens_completion_images
0
native_tokens_reasoning
4416
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
0.0475825
router
(null)
provider_responses
0
id
"resp_08c6aca1312464060169931e4d76f4819680e7fe9b7b4d6336"
status
200
is_byok
false
latency
146
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771249229-xy0rzQzxOdz2ziUVw3uz"
upstream_id
"resp_08c6aca1312464060169931e4d76f4819680e7fe9b7b4d6336"
total_cost
0.0475825
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
99.9994%
Dialogue to Total Word Ratio
Ratio: 49.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
100
99.9917%