NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PJZXRW16F91FZ94GPT129
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.3s
Cost:
$0.008820
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.89%
Dialogue to Total Word Ratio
(details)
75.9430%
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-stained floor plan across the van’s dashboard. Outside, balloons bobbed from the community hall like cheerful witnesses. “Bill, stop eating the evidence.” “It’s a cupcake, not evidence.” “It has the party logo on it.” “Then I’m destroying their branding.” She tapped the map. The presents were stacked beside the puppet stage, guarded by one grandmother, two clowns, and a suspicious golden retriever. “We go in as entertainers,” Molly said. “I hate puppets.” “You are not the puppet. You are Professor Pickle, balloon scientist.” Bill stared at the squeaky green wig in his lap. “That title comes with tenure?” “It comes with access to the gift table.” “And what are you?” “Madame Twinkles, face painter and distraction specialist.” “You once painted a tiger that looked like a tax accountant.” “It was abstract.” Inside the hall, children shrieked with joy. Bill flinched. “That sound is illegal.” “That sound means cake soon. Cake means chaos.” He adjusted his fake mustache, which immediately fell into his tea. “Molly, maybe stealing from children is low.” She paused, then sighed. “Fine. We only steal the presents marked from Uncle Gary.” “Why?” “Nobody likes Gary.” Bill grinned. “A noble heist, then.” “The noblest.”
created_at
"2026-04-24T21:33:29.922Z"
4/24/2026, 9:33:29 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
687
moderation_latency
(null)
generation_time
10196
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
66
native_tokens_completion
283
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
0.00882
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_079e476c2af48b2d0169ebe1aa087c819490ee6d56eb75d489"
is_byok
false
latency
272
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-1777066409-asnBmLQsZ4ZesaNbZlyy"
session_id
(null)
api_type
"completions"
id
"gen-1777066409-S8gqRROCFd1GEcu24qPh"
upstream_id
"resp_079e476c2af48b2d0169ebe1aa087c819490ee6d56eb75d489"
total_cost
0.00882
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
199
51.89%
Dialogue to Total Word Ratio
Ratio: 59.00%, Deviation: 9.00%
neededClean
false
wordsTotal
200
wordsDialogue
118
75.9430%