NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKARXJB4G50PHA6JREG0MAG
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.1s
Cost:
$0.014332
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 stared at the garish bouncy castle. "Bill, this is your most evil idea yet." "It's a strategic redistribution of unwrapped assets." "They're toddlers, not oligarchs." "Exactly. Low security, high yield, maximum cake." "We are not stealing cake." "Fine, just the presents. Look at those gift bags. They're practically begging for a more appreciative home." "How do you propose we get past the balloon arch of doom?" "We blend in. You're Aunt Molly from out of town. I'm your disappointing plus-one." "Believable. I do look like I judge people’s juice boxes." "I'll ‘accidentally’ knock over the magician's top hat, create confusion, you sweep the gift table." "And when someone notices the mountain of missing Paw Patrol?" "Blame the magician. Everyone already half suspects witchcraft." "What about the clown?" "I've never lost a staring contest with a grown adult in a rainbow wig." "You cried at that mascot in the mall." "It stepped on my nachos. Totally different scenario." "Fine. What’s the getaway plan?" "Inflatable slide. We ride down, bags in hand, into the alley." "That is the stupidest, loudest exit ever." "Kids will think it's part of the show." Molly sighed, already reaching for her striped party socks before leaving.
created_at
"2026-02-16T13:38:43.128341+00:00"
2/16/2026, 1:38:43 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15849
moderation_latency
(null)
generation_time
17510
tokens_prompt
77
tokens_completion
436
native_tokens_prompt
66
native_tokens_completion
1425
native_tokens_completion_images
0
native_tokens_reasoning
1141
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
0.0143325
router
(null)
provider_responses
0
id
"resp_08d13d1e29b92d830169931dd088dc8197a4e60a23dd32cec9"
status
200
is_byok
false
latency
161
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771249104-aPQVrGrgw0gRGqIEZe6W"
upstream_id
"resp_08d13d1e29b92d830169931dd088dc8197a4e60a23dd32cec9"
total_cost
0.0143325
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
99.9881%
Dialogue to Total Word Ratio
Ratio: 91.04%, Deviation: 1.04%
neededClean
false
wordsTotal
201
wordsDialogue
183
99.9935%