NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09RH5WT72AH79M0338VAPR
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.2s
Cost:
$0.001417
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.04%
Dialogue to Total Word Ratio
(details)
46.8471%
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 hedge in a black beanie and a grin that had done time in three counties. Beyond the garden fence, balloons bobbed like cheerful sentries over a children’s party, and the smell of cake drifted out every time the patio door opened. Bill adjusted his gloves and peered through the slats. “That’s a lot of wrapping paper,” he whispered. “And a lot of trust,” Molly said. Inside, children shrieked around a magician whose rabbit seemed to have given up on magic entirely. A mountain of presents glowed beneath a paper banner reading HAPPY BIRTHDAY, BEN. Bill swallowed. “We’re really stealing from children?” Molly checked her watch with professional dignity. “We’re liberating gifts from an inefficient distribution system.” Bill frowned at the lopsided piles. “What’s the plan?” Molly produced a hand-drawn map, two lollipops, and a tiny trolley. “You distract the clown,” she said, “I’ll handle the loot.” “There’s a clown?” “Apparently.” A cheer rose as someone outside popped a party popper, and the whole yard flashed with confetti. Molly pulled a face. “Perfect timing.” Bill straightened his tie, which he wore only for jobs this morally questionable. “If this goes wrong,” he muttered, “we were never here.” Molly smiled. “Bill, that’s the spirit of family fun.”
created_at
"2026-03-18T11:02:14.474Z"
3/18/2026, 11:02:14 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
465
moderation_latency
(null)
generation_time
2054
tokens_prompt
77
tokens_completion
349
native_tokens_prompt
66
native_tokens_completion
304
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
0.0014175
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_079cfd4c1ac312c70169ba86368b54819389ed0b8ed032c11d"
is_byok
false
latency
229
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-1773831734-Grs9l2Piz9vGF7TVRIrn"
upstream_id
"resp_079cfd4c1ac312c70169ba86368b54819389ed0b8ed032c11d"
total_cost
0.0014175
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
0.04%
Dialogue to Total Word Ratio
Ratio: 26.67%, Deviation: 16.67%
neededClean
false
wordsTotal
210
wordsDialogue
56
46.8471%