NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09C79YWCDHY4ZFVRTPFS4A
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.002322
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
54.72%
Dialogue to Total Word Ratio
(details)
77.3600%
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
Molly peered through the hedge. “Bill, tell me that is not a clown holding a balloon sword.” Bill adjusted his gloves. “It is, and he means business.” “You said this party would be easy.” “It is easy. They’re children. Their guard will be down.” Molly frowned. “Their guard is a clown with a balloon sword.” “Fine. Minor complication. We still take the presents.” “What’s the plan?” Bill grinned. “We mingle. We charm. We laugh at the magician’s horrible rabbit.” “Then?” “Then we follow the gift table when no one’s looking.” Molly stared. “The gift table isn’t going anywhere.” “Exactly. Efficient. No running.” “That’s your criminal mastermind strategy? Stand near the cake until everyone wanders off?” “Worked on my cousin’s wedding.” “You stole a toaster.” “I also got the napkins.” A child shrieked somewhere behind the fence, followed by delighted applause. Molly sighed. “Bill, if we get caught robbing a six-year-old’s birthday, I’m blaming you forever.” “Fair. But imagine the loot.” “The loot is wrapped in dinosaur paper.” “Dinosaur paper is premium paper.” She cracked a smile. “All right. We go in quiet.” Bill nodded. “Quiet, respectful, and emotionally detached.” “And if anyone asks?” He lifted his mask. “We’re the entertainment.”
created_at
"2026-03-18T10:55:31.148Z"
3/18/2026, 10:55:31 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2720
moderation_latency
(null)
generation_time
3108
tokens_prompt
77
tokens_completion
398
native_tokens_prompt
66
native_tokens_completion
505
native_tokens_completion_images
0
native_tokens_reasoning
207
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
0.002322
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0e0909317f0b4e510169ba84a336e88194bc422bbe1609cf94"
is_byok
false
latency
189
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-1773831331-lEPTii6LtCJ51T8jQ4qG"
upstream_id
"resp_0e0909317f0b4e510169ba84a336e88194bc422bbe1609cf94"
total_cost
0.002322
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
54.72%
Dialogue to Total Word Ratio
Ratio: 81.19%, Deviation: 8.81%
neededClean
false
wordsTotal
202
wordsDialogue
164
77.3600%