NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NK181HQE51GEJTA17NAMW
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
21.5s
Cost:
$0.039510
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9998%
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 spread a crayon map across the bakery table, pinning one corner with a jelly doughnut and another with Bill's elbow. The map showed Mrs. Puddlington's garden, the bouncy castle, the magician's suspiciously large hat, and a mountain labeled PRESENTS in purple glitter. Bill wore a cardboard crown for camouflage, though it kept sliding over one eye. Molly had chosen a unicorn sweater, reasoning that no adult questioned unicorns near cake. "We enter during musical chairs, grab gifts, then vanish behind cupcakes," Molly whispered. Bill nodded gravely, accidentally honking a party horn tucked in his pocket. Every pigeon on the windowsill judged him. Their getaway wagon waited outside, painted with flames and one apologetic daisy. It had a top speed of brisk toddler, unless pushed downhill. "Or we bring decoy presents, swap labels, and leave confusion," Bill said. Molly considered this, licking frosting from her thumb like a mastermind sampling evidence. The plan was terrible, rude, and likely to end with them face-painted as kittens by an aggressive aunt. Still, the glittering pile called to them. Bill saluted with a doughnut. Molly folded the map, leaving jam on the trampoline. Tomorrow, they would become legends, or babysitters by lunchtime, unfortunately.
created_at
"2026-04-24T21:16:02.701Z"
4/24/2026, 9:16:02 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
20398
moderation_latency
(null)
generation_time
21077
tokens_prompt
77
tokens_completion
416
native_tokens_prompt
66
native_tokens_completion
1306
native_tokens_completion_images
0
native_tokens_reasoning
1034
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
0.03951
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_04f998237a9e18220169ebdd92ca888190aa1ce1d4ecea2529"
is_byok
false
latency
232
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-1777065362-8mrmJanCCuqgHqWCVzIa"
session_id
(null)
api_type
"completions"
id
"gen-1777065362-6G1lBh7l6MN2OdGKXqNX"
upstream_id
"resp_04f998237a9e18220169ebdd92ca888190aa1ce1d4ecea2529"
total_cost
0.03951
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
100.00%
Dialogue to Total Word Ratio
Ratio: 10.45%, Deviation: 0.45%
neededClean
false
wordsTotal
201
wordsDialogue
21
99.9998%