NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA31N61825AP5BHSA6RF87
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 11s
Cost:
$0.046433
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the inflatable castle, examining a blueprint that wobbled with stains. Bill balanced a bag on his head like a ceremonial crown, the tassels flicking his ear each time someone yelled “Pinata!” They were supposed to be invisible. Instead, they were the only adults wearing capes without children attached. Molly ticked off contingencies on her fingers: rain, cake collapse, rogue magician. Bill bobbed to the party music like a buoy misplaced on a frosting sea. "Bill, it’s a cake, not a map; frosting misleads scouts." "Molly, relax; clowns love distractions, and balloons cover tactical exits." Molly sighed and adjusted their schedule, which was written on a napkin and smelled of oranges. The presents sat in a pyramid beside a cardboard castle, guarded by a paper dragon with googly eyes and a toddler who clearly understood tyranny. Bill produced a rubber chicken grappling hook; it squeaked, betraying them to three goldfish and a grandmother. The plan devolved into interpretive mime: Molly pointed, Bill nodded, the rubber chicken squeaked again. A confetti cannon fired somewhere, absolving all crimes with color. When the music surged, they surged too, sweeping the pyramid into a wagon shaped like a duck, and quacked innocently.
created_at
"2026-02-16T13:27:39.829051+00:00"
2/16/2026, 1:27:39 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
48095
moderation_latency
(null)
generation_time
71258
tokens_prompt
77
tokens_completion
869
native_tokens_prompt
66
native_tokens_completion
4635
native_tokens_completion_images
0
native_tokens_reasoning
4352
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
0.0464325
router
(null)
provider_responses
0
id
"resp_0d649ae854443a6f0169931b03d36881958f810f98007ae758"
status
200
is_byok
false
latency
165
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771248387-H3iyGv1HCuUr812iKkCD"
upstream_id
"resp_0d649ae854443a6f0169931b03d36881958f810f98007ae758"
total_cost
0.0464325
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
99.9994%
Dialogue to Total Word Ratio
Ratio: 10.50%, Deviation: 0.50%
neededClean
false
wordsTotal
200
wordsDialogue
21
99.9997%