NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM088GF3KHPH01491M99K6DW
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.2s
Cost:
$0.001710
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
9.95%
Dialogue to Total Word Ratio
(details)
35.1107%
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 crouched behind the florist’s van, eyeing the brightly colored balloons bobbing above the hedge like alarmed jellyfish. Across the street, a banner announced HAPPY BIRTHDAY, TOMMY in letters big enough to be seen from orbit. Bill adjusted his tie, which was really a length of ribbon stolen from a confectionery display, and stared at the house with grim appreciation. “Too many streamers,” Molly whispered. Bill nodded. “That’s how they get you.” The children’s party was in full swing: squeals, music, a clown with suspiciously shiny shoes, and, inside, a mountain of gifts wrapped in paper so cheerful it was practically taunting them. Molly unfolded the tiny blueprint she had drawn on a napkin. “We go in as entertainers,” she said. “You’re the magician.” “I am not a magician.” “You own a hat.” Bill considered this. “I can be a magician.” They slipped through the side gate, smiling like respectable people with deeply unserious intentions. The clown was busy inflating something unfortunate, and the parents were distracted by cake. Molly drifted toward the gift table with the serene confidence of a woman selecting ripe peaches. Bill followed, carrying a basket labeled PARTY SUPPLIES. “Just remember,” Molly murmured, “we take the presents and leave before anyone asks us to sing.” Bill grinned. “That’s the real crime.”
created_at
"2026-03-18T10:36:00.881Z"
3/18/2026, 10:36:00 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1720
moderation_latency
(null)
generation_time
3020
tokens_prompt
77
tokens_completion
371
native_tokens_prompt
66
native_tokens_completion
369
native_tokens_completion_images
0
native_tokens_reasoning
75
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
0.00171
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_078cc100b4b358110169ba801129508197838f543616673c5b"
is_byok
false
latency
424
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-1773830160-uFmvUFiJmzirmdDg2wHb"
upstream_id
"resp_078cc100b4b358110169ba801129508197838f543616673c5b"
total_cost
0.00171
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
9.95%
Dialogue to Total Word Ratio
Ratio: 22.33%, Deviation: 12.33%
neededClean
false
wordsTotal
215
wordsDialogue
48
35.1107%