NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA5KYH0JYAH8YQXA1B7YH0
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
40.0s
Cost:
$0.027273
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 pressed her back against the low hedge, peering through plastic leaves at the chaos in the backyard. Toddlers swarmed a bouncy castle like tiny, sticky pirates. Parents clutched paper cups and the last shreds of their dignity. A mountainous pile of wrapped presents glittered beside the cake. "So, we smile, grab the loot, and nobody cries except the clown," Molly whispered. Bill adjusted his fake caterer’s cap, which clearly used to be a shower cap in another life. "Define smile," Bill muttered, eyeing the balloon arch. He winced as a magician produced a live rabbit from an exhausted-looking hat. The children screamed with joy; the rabbit screamed silently. “Friendly, not felony,” she said. Bill studied the presents. Dinosaur wrapping. Unicorns. Something that actually involved glitter and malice. “Big moral difference,” Bill replied. He flicked open the catering clipboard. Inside, instead of menus, he’d taped a meticulous floor plan of the house, all exits and potential Lego hazards marked in red. A kid lobbed a cupcake over the fence. It splatted near Molly’s boot like a pastel grenade. She decided it was time to infiltrate, straightening her borrowed nametag: AUNT SANDRA for the most awkward job she’d taken all week.
created_at
"2026-02-16T13:28:32.649615+00:00"
2/16/2026, 1:28:32 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9833
moderation_latency
(null)
generation_time
39888
tokens_prompt
77
tokens_completion
950
native_tokens_prompt
66
native_tokens_completion
2719
native_tokens_completion_images
0
native_tokens_reasoning
2442
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
0.0272725
router
(null)
provider_responses
0
id
"resp_00949aadfc06472c0169931b581b8c8193b70b626237b3abe4"
status
200
is_byok
false
latency
204
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248472-lpNE0Z8LAvZsVGzEHQS6"
upstream_id
"resp_00949aadfc06472c0169931b581b8c8193b70b626237b3abe4"
total_cost
0.0272725
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
99.9995%