NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA5FM4CKFB4M1VXFSH49VV
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
42.9s
Cost:
$0.015953
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 pressed her nose against the community center window, fogging a circle. Inside, balloons bobbed and children screamed like tiny car alarms. "Look at all those presents," she whispered. "It’s like Santa’s storage unit exploded." Bill adjusted his ski mask with offended dignity. "It’s a unicorn-themed party, Molly. We’re about to rob a mythical horse." "Unicorns aren’t horses, Bill. They’re… hornier." "Please never say that again." She unfolded a crayon-smeared invitation. "Newsflash, my cousin invited us. We are technically guests." "Technically, your cousin thinks we’re helping with the magic show." "We are," Molly said. "We’re making the gifts disappear." Bill peeked through the door crack as a clown tripped over a cupcake. "Security detail appears to be frosting-based." "Even better," she said. "Sugar high kids move faster than guards; chaos is cover." "Fine. You distract them. Do juggling. Or taxes. Kids hate taxes." "I’ll start a rumor the cake has broccoli filling." "You’re a monster." "Monster with a gift bag," Molly said. "Once the birthday kid blows out the candles, lights go off, we wheel in the laundry cart, load the haul, vamoose." Bill sighed. "If we get caught, I’m telling everyone you’re the clown." Molly grinned, already pocketing hats.
created_at
"2026-02-16T13:28:30.810451+00:00"
2/16/2026, 1:28:30 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10076
moderation_latency
(null)
generation_time
42363
tokens_prompt
77
tokens_completion
877
native_tokens_prompt
66
native_tokens_completion
1587
native_tokens_completion_images
0
native_tokens_reasoning
1283
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
0.0159525
router
(null)
provider_responses
0
id
"resp_0ae9401e4f12286e0169931b53ac1c8196a4ffd03aa0393c67"
status
200
is_byok
false
latency
141
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248467-5zOVhiS7TzTK54OJL3tI"
upstream_id
"resp_0ae9401e4f12286e0169931b53ac1c8196a4ffd03aa0393c67"
total_cost
0.0159525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
0.0009%
Dialogue to Total Word Ratio
Ratio: 68.47%, Deviation: 18.47%
neededClean
false
wordsTotal
203
wordsDialogue
139
49.9600%