NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08HR577FPC7HY2BVV1578M
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.0s
Cost:
$0.001377
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.8703%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Bill, you’re late,” Molly whispered. “I’m disguised as a balloon delivery man,” Bill said. “Do I look convincing?” “Only if the balloon delivery man is sweating like a boiled ham.” “Thank you. Now, what’s the plan?” “We enter the children’s party, blend in, and steal every present.” Bill frowned. “Every present?” “Every present.” “That’s very ambitious for a room full of sticky fingers and surveillance by mothers.” Molly adjusted her gloves. “The mothers are distracted. There’s a magician, a clown, and a cake the size of a hatchback.” “Good. I hate hatchbacks.” “Focus.” “I am focused. I’m just saying the cake has security advantages.” “Bill.” “All right, all right. We take the presents near the giant inflatable dinosaur, load them into my van, and vanish before anyone notices.” “Or before they notice and scream.” “True. Children are observant.” “And loud.” “And sticky.” “And armed with juice boxes.” Bill peered through the hedge. “What if they ask questions?” “We are party helpers.” “We are?” “You are carrying balloons.” “I thought I was the balloon delivery man.” “Same lie, better costume.” A beat passed. Bill sighed. “Molly?” “Yes?” “If this works, can we steal the cake too?” Molly smiled. “Bill, now you’re thinking like a professional.”
created_at
"2026-03-18T10:41:03.672Z"
3/18/2026, 10:41:03 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
404
moderation_latency
(null)
generation_time
1762
tokens_prompt
77
tokens_completion
417
native_tokens_prompt
66
native_tokens_completion
295
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
0.001377
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_019c162b39612fdc0169ba813fbbe48193bc90ca1d7d414da3"
is_byok
false
latency
205
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-1773830463-C8vN30u5EKYZov0tL7zz"
upstream_id
"resp_019c162b39612fdc0169ba813fbbe48193bc90ca1d7d414da3"
total_cost
0.001377
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
100.00%
Dialogue to Total Word Ratio
Ratio: 89.22%, Deviation: 0.78%
neededClean
false
wordsTotal
204
wordsDialogue
182
99.8703%