NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NF66GZ4DK4PJ0KCB6ZX68
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.1s
Cost:
$0.009780
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
93.01%
Dialogue to Total Word Ratio
(details)
89.6943%
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 flattened the birthday invitation on the dashboard with a gloved finger. Through the windshield, balloons bobbed over the community hall like suspiciously cheerful security cameras. Bill, wearing a clown wig for reasons he refused to explain, squinted at the crayon map. “Side door by the bouncy castle,” Molly said. “Terrible idea,” Bill said. “Bouncy castles squeak.” “You squeak.” “I am aerodynamic.” “You are dressed like a haunted cupcake.” Bill checked his watch, which had a picture of a duck on it. “At two-fifteen, the magician starts. Children look left, adults film badly, we enter right.” “And the presents?” “Stacked by the cake table.” Molly nodded gravely. “We take only the loudest boxes.” “The loud ones?” “Drums, whistles, robot dogs. Public service.” Bill considered this. “So we’re villains with community values.” “Exactly.” Inside the hall, a chorus of tiny voices began singing happy birthday, each child choosing a different key. Molly winced. “That’s our cue,” she said. Bill lifted a sack labeled LAUNDRY. “If anyone asks, we’re entertainers.” “You know balloon animals?” “I know balloon snake.” “That’s just a balloon.” “It’s minimalism.” They slipped from the van, tiptoed across the grass, and collided with a goat in a party hat. Bill froze. “Plan B?” he whispered. Molly sighed. “Befriend the goat.”
created_at
"2026-04-24T21:13:56.699Z"
4/24/2026, 9:13:56 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
675
moderation_latency
(null)
generation_time
8027
tokens_prompt
77
tokens_completion
411
native_tokens_prompt
66
native_tokens_completion
315
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
0.00978
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_03be436a45aeff160169ebdd14d5f48194a1a70251779a3339"
is_byok
false
latency
341
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-1777065236-ovokSOhs9xBWFB5wbThe"
session_id
(null)
api_type
"completions"
id
"gen-1777065236-xWjfp3RxAYHCIlssCVw6"
upstream_id
"resp_03be436a45aeff160169ebdd14d5f48194a1a70251779a3339"
total_cost
0.00978
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
93.01%
Dialogue to Total Word Ratio
Ratio: 44.81%, Deviation: 5.19%
neededClean
false
wordsTotal
212
wordsDialogue
95
89.6943%