NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAFMJGQJEPV10A83W7G0R6
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
39.5s
Cost:
$0.025802
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
"Stop pacing, Molly, you're wearing a groove in the sidewalk." "I'm rehearsing my innocent face, Bill. Lookâdo I scream 'beloved' 'clown' or 'felonious' 'aunt'?" "Somewhere between 'lost' 'babysitter' and 'escaped' 'raccoon.'" "Perfect, raccoons are nature's thieves. Now, the presents are under the balloon arch, right?" "Yeah, right between the bouncy castle and the chocolate fountain of doom." "Any operation involving chocolate fountains is doomed. Kids turn into syrup-coated linebackers." "That's why we blend in. I carry the empty gift bag, you carry the emotional support balloon." "An emotional support balloon?" "People respect a grown man clutching a balloon, Bill. It screams, 'I'm responsible for someone small.'" "It screams, 'I missed therapy.' But fine. After we infiltrate, what's phase two?" "Compliment the cake, create distraction. I shout, 'Is that a unicorn with realistic tax documentation?' All adults rush over." "Kids don't care about tax documentation." "Yeah, but parents do. They can't resist paperwork drama." "While they're panicking over deductible sprinkles, we sweep the presents into the gift bag." "If a kid cries?" "We promise to send postcards from College Fund Island." "Not a real place." "Neither is Santa's workshop, but look at turnout." "Remind me we're good guys?" "We're redistributing glitter."
created_at
"2026-02-16T13:34:00.169374+00:00"
2/16/2026, 1:34:00 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4969
moderation_latency
(null)
generation_time
38692
tokens_prompt
77
tokens_completion
1006
native_tokens_prompt
66
native_tokens_completion
2572
native_tokens_completion_images
0
native_tokens_reasoning
2256
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
0.0258025
router
(null)
provider_responses
0
id
"resp_07dcb3b8187d82580169931ca06e5881908911c8325e33a79a"
status
200
is_byok
false
latency
168
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248800-OTuyG64bZfJWxlxo1WWz"
upstream_id
"resp_07dcb3b8187d82580169931ca06e5881908911c8325e33a79a"
total_cost
0.0258025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
202
wordsDialogue
202
68.3860%