NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0N63QJ1KPZJGM0YH263MPP
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.7s
Cost:
$0.009510
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
67.7502%
Overall
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, it’s a children’s party, not Fort Knox.” “Bill, Fort Knox never had a bouncy castle blocking the west entrance.” “You’re seriously calling the inflatable dinosaur an entrance hazard?” “It has teeth, doesn’t it?” “It’s full of air.” “So are you, but I still plan around you.” “Fine. What’s the target?” “The present table. Pink cloth, glitter banner, suspiciously strong grandmother guarding it.” “Grandmothers don’t guard. They hover.” “This one has a handbag shaped like a brick and eyes like courtroom evidence.” “Plan?” “We arrive as entertainers.” “I am not wearing the clown trousers again.” “You stretched them.” “They were mislabeled.” “They said ‘ages six to eight.’” “Exactly. Very misleading.” “I’ll be the magician. You’re my assistant.” “Why am I always the assistant?” “Because last time you said ‘abracadabra’ and sneezed into a pigeon.” “It startled me first.” “Focus. At cake time, everyone sings. We wheel the presents out under the fake rabbit hutch.” “What about the children?” “Distracted by frosting.” “What about the parents?” “Distracted by filming frosting.” “What about the grandmother?” “You compliment her potato salad.” “Dangerous. What if it’s bad?” “Bill, for twelve wrapped boxes, you will lie.” “I’ll need hazard pay.” “You’ll get a party bag.” “With bubbles?” “If you behave.” “Deal.”
created_at
"2026-04-24T21:08:59.257Z"
4/24/2026, 9:08:59 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
776
moderation_latency
(null)
generation_time
9007
tokens_prompt
77
tokens_completion
456
native_tokens_prompt
66
native_tokens_completion
306
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.00951
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_05212719d7a9bff60169ebdbeb58808190b06a4ae1c11f1905"
is_byok
false
latency
278
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777064939-J3JQfjNukzQDzApzNkNg"
session_id
(null)
api_type
"completions"
id
"gen-1777064939-kUmyo7JVkvKrx08WbWXi"
upstream_id
"resp_05212719d7a9bff60169ebdbeb58808190b06a4ae1c11f1905"
total_cost
0.00951
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
206
67.7502%