NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NG0NH13V5EKNYJS1PTJ8H
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.2s
Cost:
$0.010110
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
99.9614%
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, explain again why we’re robbing a children’s party?” “Because, Bill, rich children receive tiny bicycles, diamond-studded dolls, and envelopes from uncles who don’t understand age-appropriate gifts.” “Right, but morally?” “Morally, we’re redistributing cake-adjacent wealth.” “I’m not wearing the clown costume.” “You absolutely are. I’m going as Sparkle the Face-Painting Fairy, and you’re Bonko.” “Bonko has enormous shoes.” “Excellent for concealing presents.” Bill stared at the map spread across the dashboard. “Why does your floor plan say ‘bouncy castle: volatile’?” “Last time, I lost a boot and three counterfeit mustaches.” “Can’t we just sneak in as caterers?” “Molly, caterers carry trays. Clowns carry chaos. Nobody questions chaos.” “That was my line.” “It’s a good line.” “Focus. At 1500 hours, the magician begins sawing the grandmother in half.” “Is that confirmed?” “No, but optimism matters. During applause, you juggle.” “I can’t juggle.” “Then drop things flamboyantly.” “And you?” “I’ll locate the gift table, deploy the sack, and compliment parents until they stop watching.” “What about the birthday child?” “I’ve prepared a distraction.” “Please don’t say ferret.” Molly lifted a wriggling shape from her handbag. “Absolutely not.” “His name is Sir Nibbles.” “We’re going to prison.” “Only if Bonko loses his nerve.”
created_at
"2026-04-24T21:14:23.803Z"
4/24/2026, 9:14:23 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
649
moderation_latency
(null)
generation_time
9054
tokens_prompt
77
tokens_completion
442
native_tokens_prompt
66
native_tokens_completion
326
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
0.01011
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0eb92ecba1c6b01f0169ebdd2fe1f48194be6cb96bc2453b88"
is_byok
false
latency
249
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-1777065263-dM7cloTuQtwzMOiGaNue"
session_id
(null)
api_type
"completions"
id
"gen-1777065263-Ke8LrGUEhnucdGkB3CyG"
upstream_id
"resp_0eb92ecba1c6b01f0169ebdd2fe1f48194be6cb96bc2453b88"
total_cost
0.01011
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.92%
Dialogue to Total Word Ratio
Ratio: 91.67%, Deviation: 1.67%
neededClean
false
wordsTotal
204
wordsDialogue
187
99.9614%