NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PTZMQG5D162ZPMVY3WRC0
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
27.9s
Cost:
$0.060150
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 bonnet of their wheezing van, pinning the corners with jelly babies, while Bill surveyed the church hall through binoculars bought from a pirate costume set. Inside, six-year-olds orbited a magician like sugared moons. Presents rose beside the cake in a glittering mountain of unicorn paper and heroic robots. Molly tapped the drawing, which showed balloons, a bouncy castle, and one stick figure labelled DANGER: GRANDMA. “Molly, those parcels are guarded by toddlers with frosting knives,” Bill whispered. “Then we go in as entertainers: you juggle, I apologize,” Molly said. Bill considered his outfit, a raccoon mask under a cardigan, and nodded with the dignity of a doomed accountant. Their previous jobs had involved diamonds, paintings, and once, by mistake, a prize marrow; none had smelled so strongly of fruit punch. Molly produced two party hats, modified with tiny suction cups for reasons she refused to explain. Bill placed his on sideways. A balloon popped inside. Both thieves dived behind a hedge, scattering jelly babies into the gutter like sugary evidence. From the hall came applause. Molly dusted leaves from her sleeves and grinned; Bill sneezed confetti. The van coughed, as if judging them.
created_at
"2026-04-24T21:37:51.781Z"
4/24/2026, 9:37:51 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
26056
moderation_latency
(null)
generation_time
27685
tokens_prompt
77
tokens_completion
431
native_tokens_prompt
66
native_tokens_completion
1994
native_tokens_completion_images
0
native_tokens_reasoning
1724
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
0.06015
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_05618b7a4b4cc02f0169ebe2afde9c81969ea5af1424390554"
is_byok
false
latency
420
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-1777066671-lT8eRGYONqi1xVDpKBGp"
session_id
(null)
api_type
"completions"
id
"gen-1777066671-fx3qcwyLtJtWPH7FQyNw"
upstream_id
"resp_05618b7a4b4cc02f0169ebe2afde9c81969ea5af1424390554"
total_cost
0.06015
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: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%