NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9RT9RRWWEFNFJHPQRSY5N
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 15s
Cost:
$0.048932
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
The stakeout wasn’t an alley so much as a parental loading zone, humming with distant squeals and the threat of glitter. Molly balanced on a milk crate throne, wearing a tiara she swore was reconnaissance camouflage. Bill held a clip art map of the venue, upside down, pretending it was a blueprint. They’d practiced their smiles in the side mirror until the mirror looked concerned. Balloons bobbed against the dusk like thought bubbles filled with frosting. Somewhere, a mascot sneezed confetti. The objective sat inside: a mountainous altar of packages, squeaky with ribbons, smug with tape, begging for victimless redistribution. "Bill, we are not stealing joy, only relocating wrapping opportunities." "Molly, my conscience packed snacks; it says plan needs napkins." "Relax, we arrive, admire balloon animals, and liberate squashed corners." "Liberate? Word makes bows lawyer up and ribbons request protection." "Bill, picture it: a noble heist against tyrannical gift-wrapping bureaucracy." "Picture it: thirty toddlers forming militias with frosting and kazoos." "We blend in: party hats, oohs, compliments on tape craftsmanship." "And when someone asks names, we improvise: Clutch and Ribbonstein?" "Then we redistribute weight: you handle decoys, I handle diplomacy." "Fine, but if cake flies, we retreat behind piñatas, dignity."
created_at
"2026-02-16T13:22:08.382785+00:00"
2/16/2026, 1:22:08 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
37530
moderation_latency
(null)
generation_time
74874
tokens_prompt
77
tokens_completion
1226
native_tokens_prompt
66
native_tokens_completion
4885
native_tokens_completion_images
0
native_tokens_reasoning
4544
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
0.0489325
router
(null)
provider_responses
0
id
"resp_08606a3a32c5654301699319b49ca4819394bf73c05e0c7587"
status
200
is_byok
false
latency
150
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771248052-BgT6UKNpQ66TTNZ9qI6m"
upstream_id
"resp_08606a3a32c5654301699319b49ca4819394bf73c05e0c7587"
total_cost
0.0489325
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%