NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AWAN97ZDGAW4SN9X0YKW1
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.7s
Cost:
$0.003227
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
25.33%
Dialogue to Total Word Ratio
(details)
60.6607%
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 peered through the bakery window at the balloon-lit house across the street. "That party is a gold mine," she whispered. "A confetti mine," Bill replied, adjusting his tie, "which is worse for the shoes." Inside, a chorus of squeals rose every time the gift table groaned under another wrapped package. "We go in as entertainers," Molly said. "Entertainers?" "Yes. You are a magician." "I am terrible at magic." "Perfect. Children adore failures if they wear a cape." Bill frowned. "And you?" "I am the clown's mysterious assistant." "You hate clowns." "Exactly. No one expects sincerity from a clown-adjacent woman." Bill watched a parent photograph a towering cake. "What's the extraction route?" "Front door, through the kitchen, out the laundry, and into the van." "The van with the expired circus decals?" "The very same. It screams innocence." Bill grinned. "And the presents?" "We sort them later." "You mean tomorrow?" Molly nodded. "We are criminals, Bill, not monsters. Tonight we only take the gifts." He lifted his hat. "For the children?" "For the children," she said, and both of them, impossibly, looked almost noble as the first trumpet of the party soundtrack began.
created_at
"2026-03-18T11:21:47.444Z"
3/18/2026, 11:21:47 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3269
moderation_latency
(null)
generation_time
3586
tokens_prompt
77
tokens_completion
298
native_tokens_prompt
66
native_tokens_completion
706
native_tokens_completion_images
0
native_tokens_reasoning
423
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
0.0032265
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0242b4808e8ee5a40169ba8acb804c819583f63a1787971405"
is_byok
false
latency
188
model_permaslug
"openai/gpt-5.4-mini-20260317"
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-1773832907-IAJIkVMv7umrAvTzz8sM"
upstream_id
"resp_0242b4808e8ee5a40169ba8acb804c819583f63a1787971405"
total_cost
0.0032265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
25.33%
Dialogue to Total Word Ratio
Ratio: 60.82%, Deviation: 10.82%
neededClean
false
wordsTotal
194
wordsDialogue
118
60.6607%