NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0916DGH8ABH6JYA587NW12
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
24.0s
Cost:
$0.021330
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 van window at the bouncy castle glowing in the park. Music, fairy lights, and squeals of children floated over the fence. Bill adjusted his tie, a stolen tie, and sighed at the row of boxes stacked under a banner. Molly checked the guest list she had swiped from a coat pocket. The party theme was Sparkle Patrol, explaining the capes, glitter, and plastic stars. Perfect cover. She produced a clown nose, a ladder, and two lanyards labeled HELPING HANDS. Bill, with the face of a disappointed librarian, put on the lanyard with courage. “Remember the cupcakes. We’re only here for presents, not chaos,” Molly whispered. “Good. I hate crying children and consequences today very much,” Bill said. They slipped through the side gate behind a parent balancing plates. Nobody noticed two volunteers heading for the gift table where the presents sat like treasure. Molly flashed a grin at a toddler. Bill saluted the magician. The magician never looked up; the children were too busy cheering confetti. By the time the cake was cut the van was packed, the teddy bear was sulking on the dashboard, and Molly was planning their exit route through the balloon arch.
created_at
"2026-03-18T10:49:29.788Z"
3/18/2026, 10:49:29 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
23524
moderation_latency
(null)
generation_time
23812
tokens_prompt
77
tokens_completion
1114
native_tokens_prompt
66
native_tokens_completion
4729
native_tokens_completion_images
0
native_tokens_reasoning
4468
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
0.02133
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_099df3c76473417c0169ba8339dfbc8195911de620ffceabd6"
is_byok
false
latency
231
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-1773830969-94gKVSJJ90Btqr4lV6do"
upstream_id
"resp_099df3c76473417c0169ba8339dfbc8195911de620ffceabd6"
total_cost
0.02133
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%