NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GAMWGW23RZDWM870J5B1C
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.1s
Cost:
$0.004800
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
45.29%
Dialogue to Total Word Ratio
(details)
67.8867%
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 crouched behind the garden wall, peering at balloons bobbing above the hedge like surveillance blimps. Bill unfolded a crayon-smeared invitation as if it were blueprints for a bank job. “Three o’clock cake,” Molly whispered. “That’s when the adults get sentimental and useless.” “Useless? Last time a grandmother hit me with a juice box,” Bill said. “You were rattling a piñata with a screwdriver.” “I was checking for alarms.” Beyond the hedge, children shrieked around a bouncy castle shaped like a pirate ship. Presents glittered on a table under a banner reading HAPPY SIXTH, OLIVER. “Look at that haul,” Molly said. “Board games, remote-control dinosaurs, suspiciously square boxes. It’s a gold mine with wrapping paper.” Bill adjusted his flat cap. “What’s the exit strategy?” “Simple. You pose as the magician’s assistant.” “There’s a magician?” “There will be if you flap your arms confidently.” Bill stared. “And you?” “I’ll infiltrate the kitchen, neutralize the sausage rolls, and secure the gift table.” “That is not a plan. That is a cry for help.” Molly grinned and produced two paper party hats. “Disguises.” Bill accepted one with tragic dignity. “If I die under a banner font like that, I’m haunting you specifically.” “Good,” Molly said. “Now smile. Nothing alarms parents like a frown.”
created_at
"2026-03-06T12:00:32.373Z"
3/6/2026, 12:00:32 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
485
moderation_latency
(null)
generation_time
8649
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
66
native_tokens_completion
309
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0048
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_01b63c27e2ae2a2b0169aac1e091e08195bc9f3d9cbfd2a9ac"
is_byok
false
latency
157
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772798432-EeGXMSZO4U9mxNfHnugp"
upstream_id
"resp_01b63c27e2ae2a2b0169aac1e091e08195bc9f3d9cbfd2a9ac"
total_cost
0.0048
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
45.29%
Dialogue to Total Word Ratio
Ratio: 59.43%, Deviation: 9.43%
neededClean
false
wordsTotal
212
wordsDialogue
126
67.8867%