NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA87T2665B4XW9YAJ7M6M9
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.5s
Cost:
$0.008743
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
Balloons bobbed above the backyard fence. “We’re robbing a birthday party now? This is a new moral low, even for us.” “Relax, Molly. Kids have short memories and a lot of sugar. They’ll blame the clown.” “The clown is you, Bill. You’re literally wearing the nose.” “It’s a disguise. I blend in. Observe: innocent jester, not hardened criminal.” “Innocent jesters don’t carry crowbars in gift-wrap.” “It’s festive. Also, duct tape has unicorns on it. We’re thematically consistent.” “Walk me through this again. Why not a bank, a museum, something classy?” “Because banks have lasers, and five-year-olds have gelatinous snacks and poor situational awareness.” “So we sneak in, yell ‘Happy Birthday,’ grab everything with a bow, and run?” “Almost. We mingle first. Eat cake, establish alibis, then liberate the merchandise.” “Liberate? Bill, these are Paw Patrol puzzles, not priceless artifacts.” “Value is subjective. Have you seen toy prices? This is basically a high-yield heist.” “What about witnesses under four feet tall?” “Easily distracted. I’ll shout ‘Piñata!’ You sweep the presents into the sack.” “And if someone’s actually hitting a piñata?” “Then we yell ‘Double piñata!’ and improvise.”
created_at
"2026-02-16T13:29:36.852882+00:00"
2/16/2026, 1:29:36 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6533
moderation_latency
(null)
generation_time
18132
tokens_prompt
77
tokens_completion
774
native_tokens_prompt
66
native_tokens_completion
866
native_tokens_completion_images
0
native_tokens_reasoning
557
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
0.0087425
router
(null)
provider_responses
0
id
"resp_01fed5a61e5e242b0169931bae035c819586d9364469fd9ae5"
status
200
is_byok
false
latency
214
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248557-ZQYXvX2KpaQHVGUvEaxK"
upstream_id
"resp_01fed5a61e5e242b0169931bae035c819586d9364469fd9ae5"
total_cost
0.0087425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.4837%
Matches word count
n/a
neededClean
false
words
190
80.3194%
Dialogue to Total Word Ratio
Ratio: 96.84%, Deviation: 6.84%
neededClean
false
wordsTotal
190
wordsDialogue
184
85.4016%