NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9TTVYEAMVHNY5YK7KVDYK
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
46.9s
Cost:
$0.008677
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
Under the fluorescent bunting Molly and Bill crouched behind a folding table, whispering like criminals rehearsing a lullaby. They admired a cupcake tower, mental maps of ribbon and tape forming. A helium dog bobbed, tethered to a chair, optimistic and oblivious. Their plan smelled faintly of frosting and mischief. They argued over timing, routes, and escape velocity with the seriousness of surgeons discussing pastries. A parent practiced "Happy Birthday" on a paper plate nearby. The playlist promised sugar and chaos. They checked tiny hands, checked lists, checked each other's bravery. Night light glowed; the house hummed with bubblegum intent delicious. "Molly: We knock over the cupcake tower, start the sugar tide, and as adults corral chaos we unwrap confidence, slide presents under coats, whispering apologies to Santa." "Bill: What about tiny hands and parental radar? We need a clean exit, matching sippy cup decoys and a stroller escape route, heartbeats timed to the candles." "Molly: Two minutes, three at most. We divide and conquer: you take east room, I take west. No gifts left, no glitter fingerprints. We leave a ribbon bouquet for theatrics and a note signed 'The Thank You Fairy.' Also bring mittens and a tiny trombone please."
created_at
"2026-02-16T13:22:45.976418+00:00"
2/16/2026, 1:22:45 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7060
moderation_latency
(null)
generation_time
46688
tokens_prompt
77
tokens_completion
1435
native_tokens_prompt
66
native_tokens_completion
4330
native_tokens_completion_images
0
native_tokens_reasoning
4032
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
0.0086765
router
(null)
provider_responses
0
id
"resp_075cd3af331dbe6d01699319f6bcf8819098f5b6f57f004e57"
status
200
is_byok
false
latency
154
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248118-NwlfnscQagup7SU6Fd6b"
upstream_id
"resp_075cd3af331dbe6d01699319f6bcf8819098f5b6f57f004e57"
total_cost
0.0086765
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
99.9900%
Dialogue to Total Word Ratio
Ratio: 51.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
102
99.9950%