NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKATSFFK778WVN1MAG54SH2
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
53.5s
Cost:
$0.012105
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 smirks under a party hat, phone map glowing brightly "We slip in after the magician finishes the cake trick" Bill checks his watch like a conspiratorial metronome now "Grab all wrapped boxes while kids chase that balloon clown" They creep through streamers and spilled glitter, grinning smiles "We dodge the parents by hiding behind the piñata pole" A dachshund steals a cupcake and slows their progress "I'll distract with fake balloon animal tricks and loud honk" Molly whispers a plan, precise as pastry folding instructions "Swaddle the fragile presents in party napkins like miniature burritos" Bill nods, smuggling a confetti cannon behind his jacket "Leave nothing but crumbs and a suspiciously empty piñata stick" They pause at a throne where a toddler naps "We split at the back gate and meet by oak" Outside the moon is a spotlight on their heist "Our van will be disguised as caterer truck with glitter" They tuck presents into pillowcases and beneath scarves fast "If a toddler notices, offer juice and perform a nap" A parent asks directions; Bill gives a wild lie "We vanish into the night carrying ribbons, bows, and cake" They dash past party lights, hearts drumming like tambourines
created_at
"2026-02-16T13:40:19.871435+00:00"
2/16/2026, 1:40:19 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2826
moderation_latency
(null)
generation_time
53320
tokens_prompt
77
tokens_completion
1235
native_tokens_prompt
66
native_tokens_completion
6044
native_tokens_completion_images
0
native_tokens_reasoning
5760
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
0.0121045
router
(null)
provider_responses
0
id
"resp_0fe3c4b8d111a8900169931e0de6748197bb0816cc67aaad26"
status
200
is_byok
false
latency
872
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249165-ewKhqkQ9JRU6sTjZtqjn"
upstream_id
"resp_0fe3c4b8d111a8900169931e0de6748197bb0816cc67aaad26"
total_cost
0.0121045
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%