NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P2AT1XBJ5WQ0HY2SXG4XS
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.6s
Cost:
$0.008790
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
82.08%
Dialogue to Total Word Ratio
(details)
91.0297%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unfolded the crayon-drawn map across the bonnet of their van, weighting the corners with a stale doughnut, a bent screwdriver, and Bill’s emergency kazoo. Across the street, balloons bobbed outside number seventeen, where thirty sugar-crazed children were shrieking beneath a banner reading HAPPY BIRTHDAY, TIMMY. “Clowns first, cake second, presents third,” Molly said. Bill squinted through binoculars held backwards. “That pony looks tactical.” “It’s a donkey in a hat.” The plan was elegant, if one ignored the glitter glue. Molly would enter disguised as Princess Sparkleboots, distract the parents with balloon animals resembling tax forms, and herd the children toward the garden. Bill would slip in as Uncle Kevin, a man nobody remembered inviting but everyone felt too polite to question, and load the presents into the van marked HAPPY FUN MAGICIANS. Inside his satchel, Bill carried labels reading EDUCATIONAL TOYS, the most boring camouflage known to childhood. “What if they ask for a trick?” Bill said. “Pull humility from your sleeve.” He patted his jacket nervously, producing three lollipops, a parking ticket, and a rubber chicken with judgmental eyes. The front door opened. A toddler wearing a cape pointed directly at them and yelled, “Mum, the burglars are here early!”
created_at
"2026-04-24T21:24:24.01Z"
4/24/2026, 9:24:24 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
727
moderation_latency
(null)
generation_time
8545
tokens_prompt
77
tokens_completion
351
native_tokens_prompt
66
native_tokens_completion
282
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
0.00879
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_07f0bbca8743e0fc0169ebdf881820819495cc2e146b849730"
is_byok
false
latency
238
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-1777065864-rBVQripGGXfAJ7curTB9"
session_id
(null)
api_type
"completions"
id
"gen-1777065864-ibUXoSGvoKm8HBZtIZiN"
upstream_id
"resp_07f0bbca8743e0fc0169ebdf881820819495cc2e146b849730"
total_cost
0.00879
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
82.08%
Dialogue to Total Word Ratio
Ratio: 16.67%, Deviation: 6.67%
neededClean
false
wordsTotal
204
wordsDialogue
34
91.0297%