NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9Z2XMCPMER4VYDTDDM3BS
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
49.5s
Cost:
$0.007931
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 huddle under a fake fern, whispering a heist plan that smells faintly of cupcakes. Molly: "We dress as clowns, steal the cake, take the loot, vanish." Bill: "What about the pony cake topper and the glitter bomb?" Molly: "Parents will be distracted by balloons and interpretive singing." Bill: "Kids will cry, chaos covers our tracks, we smile and leave." Molly: "But the puppy guardian might growl." Bill: "We bring a squeaky toy and a treat." Molly: "Quick in, out via kitchen, claim moral ambiguity." Bill: "What about small surprises? Candy, socks, glittery hats." Molly: "We wear party masks, leave a signed apology note." Bill: "Deal. We split evenly, including the singing fish." Molly: "Tonight we become legends to toddlers, villains to librarians, heroes to ourselves." They map escape routes around cake tables and suspicious uncles, rehearsing faux confetti falls and an emergency dad joke. A glitter trail is optional, moral doubt is negotiable, and the real prize may be the shared absurdity. They exchange a crooked grin, palms meeting over a curling ribbon, then melt into the party crowd like two suspiciously cheerful shadows on a sugar high with a vague retirement plan involving sunscreen and margaritas.
created_at
"2026-02-16T13:25:07.955795+00:00"
2/16/2026, 1:25:07 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5418
moderation_latency
(null)
generation_time
49278
tokens_prompt
77
tokens_completion
1451
native_tokens_prompt
66
native_tokens_completion
3957
native_tokens_completion_images
0
native_tokens_reasoning
3648
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
0.0079305
router
(null)
provider_responses
0
id
"resp_07390a21ea42946b0169931a820f88819391de499d08fcfdff"
status
200
is_byok
false
latency
117
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248257-UAQ1709wKknPpsc3eNqN"
upstream_id
"resp_07390a21ea42946b0169931a820f88819391de499d08fcfdff"
total_cost
0.0079305
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%