NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NF2MRKD45YC159AV89RAH
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
49.9s
Cost:
$0.100380
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
97.09%
Dialogue to Total Word Ratio
(details)
98.5438%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 a crayon map on the alley dumpster. Bill, disguised in a balloon-animal hat, watched the church hall shimmer with streamers, parents, and the terrifying music of sugar. “Right. We enter during pass-the-parcel, blend with the magicians, and liberate the glittery loot.” “Liberate? They’re teddy bears, not prisoners.” “Everything in wrapping paper is oppressed.” “What if a child asks my age?” “Say you’re tall for six.” “I’m thirty-eight.” “Extremely tall.” “What if they make me dance?” “Then dance criminally.” “What if there’s a clown?” “Bill, focus. The bicycle is our crown jewel.” “You don’t ride bicycles.” “I could learn. Crime needs cardio.” “You once got winded opening a biscuit tin.” “That tin was fortified.” A paper crown skittered over and stuck to Molly’s boot. She kicked it off with professional disdain, slipped on a cupcake, and landed in a recycling bin with a small heroic honk. “Maybe the universe objects.” “The universe can queue.” They peered through the window. Beneath HAPPY BIRTHDAY, GRACIE! a girl hugged a three-legged rescue dog. “We’re stealing from a dog girl?” Molly folded the map. “Fine. We steal cake and donate better balloons.” Bill nodded, already calculating whether frosting counted as portable treasure tonight.
created_at
"2026-04-24T21:13:53.056Z"
4/24/2026, 9:13:53 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
45907
moderation_latency
(null)
generation_time
49767
tokens_prompt
77
tokens_completion
615
native_tokens_prompt
66
native_tokens_completion
3335
native_tokens_completion_images
0
native_tokens_reasoning
3041
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
0.10038
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0e58a1ce4732cf900169ebdd112330819091d853b6e3f458bd"
is_byok
false
latency
270
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-1777065233-VLHhqHKgCqYHfHwwVBfF"
session_id
(null)
api_type
"completions"
id
"gen-1777065233-9nCPZV477DHaIxNchDez"
upstream_id
"resp_0e58a1ce4732cf900169ebdd112330819091d853b6e3f458bd"
total_cost
0.10038
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
97.09%
Dialogue to Total Word Ratio
Ratio: 54.15%, Deviation: 4.15%
neededClean
false
wordsTotal
205
wordsDialogue
111
98.5438%