NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A0KDB9HZ3SH3G6XGDYW0Q
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.7s
Cost:
$0.001741
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
34.0511%
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 hedge, peering at the fairy-lit house. “Right, Bill, tonight we become festive legends.” Bill adjusted his too-small Santa hat. “I’ve always wanted a legend with more tinsel.” “Focus. The party starts at six, the cake arrives at six-thirty, and the presents are piled by the piano.” “Piano? Marvelous. I can only lift with musical accompaniment.” Molly sighed. “You are not lifting with musical accompaniment. You’re carrying the sack.” Bill glanced at the tiny velvet bag. “This sack looks optimistic.” “It’s a children’s party, Bill. The gifts are small, but numerous. Think of it as volume theft.” He nodded solemnly. “My specialty. I once stole twelve jam doughnuts and a brass doorknocker.” “Exactly. We mingle, compliment the balloon animals, and wait for the magician to distract the parents.” Bill grinned. “And then?” “And then we sweep in, collect the presents, and leave before anyone notices the missing train set.” “Brilliant,” Bill whispered. “What if they ask our names?” Molly straightened her gloves. “We’re not names tonight. We’re caterers.” Bill’s eyes widened. “Do caterers usually have one fake moustache?” “No.” “Excellent. I’m already suspicious.”
created_at
"2026-03-18T11:06:38.901Z"
3/18/2026, 11:06:38 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1732
moderation_latency
(null)
generation_time
3594
tokens_prompt
77
tokens_completion
357
native_tokens_prompt
66
native_tokens_completion
376
native_tokens_completion_images
0
native_tokens_reasoning
92
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
0.0017415
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_01b0abf3a3da0f520169ba873f099081949d0558dc58f5f176"
is_byok
false
latency
504
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-1773831998-DRJPnoVebSuCuB7d5T8K"
upstream_id
"resp_01b0abf3a3da0f520169ba873f099081949d0558dc58f5f176"
total_cost
0.0017415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
0.00%
Dialogue to Total Word Ratio
Ratio: 78.31%, Deviation: 28.31%
neededClean
false
wordsTotal
189
wordsDialogue
148
34.0511%