NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PD8TW4VPA153S6MWH94BX
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.1s
Cost:
$0.010440
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
98.04%
Dialogue to Total Word Ratio
(details)
98.3771%
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
“Bill, explain again why we’re robbing a birthday party.” “Because, Molly, nobody guards a bouncy castle with the seriousness it deserves.” “They’re children’s presents.” “Unopened children’s presents. Could be jewelry.” “Could be socks with dinosaurs.” “Dinosaurs are valuable in bulk.” “You said this was a high-end target.” “It is. The invitation had glitter.” “Glitter is not financial intelligence.” “It stuck to my elbow for three days. That’s commitment.” “What’s the entry plan?” “We arrive disguised as entertainers.” “Please tell me you didn’t book us as clowns.” “Of course not. Clowns attract scrutiny.” “Good.” “We’re balloon magicians.” “Bill.” “I learned a dog.” “That is not a complete act.” “It’s a loyal beginning.” “And while you’re twisting rubber mammals, I do what?” “You mingle near the gift table and deploy the decoy.” “The decoy?” “A piñata labeled ‘Free Candy.’” “At a children’s party? That’s not a decoy, that’s a riot.” “Exactly. Chaos, shrieking, frosting everywhere.” “You’ve planned this like a man banned from six bakeries.” “Seven, pending appeal.” “Masks?” “Party hats.” “Getaway?” “Ice-cream truck.” “You stole an ice-cream truck?” “Borrowed. It plays ‘Greensleeves’ menacingly.” “Molly, Bill,” called a small voice from behind them, “Mom says you’re late.” They froze. Bill whispered, “Abort?” Molly sighed. “Bring the balloon dog.”
created_at
"2026-04-24T21:30:22.435Z"
4/24/2026, 9:30:22 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1023
moderation_latency
(null)
generation_time
10020
tokens_prompt
77
tokens_completion
480
native_tokens_prompt
66
native_tokens_completion
337
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
0.01044
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0b43ced6910eef340169ebe0ee88448194be061e590a806f2a"
is_byok
false
latency
296
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-1777066222-pgIgEdodRkwHOG4BdKtP"
session_id
(null)
api_type
"completions"
id
"gen-1777066222-cNhHBrmBu7Cah3RdnmEx"
upstream_id
"resp_0b43ced6910eef340169ebe0ee88448194be061e590a806f2a"
total_cost
0.01044
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
98.04%
Dialogue to Total Word Ratio
Ratio: 93.75%, Deviation: 3.75%
neededClean
false
wordsTotal
208
wordsDialogue
195
98.3771%