NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAG0KWTP1PVHDHT08M863P
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
43.4s
Cost:
$0.007737
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 and Bill crouched behind a stack of folding chairs, whispering like conspiratorial squirrels. The children's party raged inside with glitter hurricanes, balloon animals and a suspiciously emotional clown. They plotted routes around parental eyes and snack tables, timing recess screams like alarms. Bill polished a tiny crowbar with a napkin while Molly sketched a map of sugar graveyards. Both wore businesslike grins and ridiculous hats; their van idled blocks away, humming tunes. Every scheme smelled faintly of frosting and bad decisions. Outside, a dog barked twice, which they had prearranged as their signal to dash, grab boxes and vanish. "Molly: We wear dinosaur costumes, sneak in with confetti hoses." "Bill: No, clowns are safer. Kids expect clowns, not thieves." "Molly: Friends will hand us gifts during group games." "Bill: We'll replace wrapping with identical paper so parents never notice." "Molly: Exit through the bouncy castle, quick and slippery." "Bill: Bring a cake distraction. Everyone distracted equals perfect pilfering." "Molly: I want the unicorn piƱata. Glitter hides fingerprints for effect." "Bill: What about a toddler with a sticky fist?" "Molly: Bribe them with cookies, they follow crumbs to our van." "Bill: Cookies and clowns. Molly, you're a criminal genius, truly."
created_at
"2026-02-16T13:34:16.902962+00:00"
2/16/2026, 1:34:16 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1917
moderation_latency
(null)
generation_time
43039
tokens_prompt
77
tokens_completion
1379
native_tokens_prompt
66
native_tokens_completion
3860
native_tokens_completion_images
0
native_tokens_reasoning
3520
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
0.0077365
router
(null)
provider_responses
0
id
"resp_02315be49c3298c40169931cacc1dc8196bb61892fda00015d"
status
200
is_byok
false
latency
125
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248812-fGA075Mqpaq63dEL3w7P"
upstream_id
"resp_02315be49c3298c40169931cacc1dc8196bb61892fda00015d"
total_cost
0.0077365
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%