NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08P0FQ0ED4BRMH8F8DAGW8
Run Details
Model:
GPT-5.4 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1.8s
Cost:
$0.000388
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3860%
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, whisper. This is a children’s party, not a bank.” “Bill, same blueprint: cheerful exterior, panic interior.” “Presents are basically cash in glitter.” “Exactly. Now listen—when the clown arrives, we take the gift pile first, then the stockings, then we pretend we were there for the face paint.” “Pretend? Molly, we can’t even pretend we like peas.” “We’ll wear the party hats. Kids love hats. Also, nobody questions a person who looks mildly confused.” “I’m always mildly confused.” “That’s the best kind.” “What if the parents catch us?” “Then we charm them with innocent compliments like, ‘Wow, your birthday candles are very aerodynamic.’” “That sentence will not land.” “It’ll distract them long enough for you to grab the good stuff.” “What’s good stuff?” “Anything wrapped in satin. And the toy that makes noise. Parents can’t resist noise.” “Last time I stole a toy, I tripped over a balloon and a toddler asked me why I looked sad.” “This time no sadness. This time we look like we just forgot a password.” “We don’t have a password.” “Then make one up. ‘GlitterGlory123.’” “That’s not a real—” “Shh. The door. Smile like you’re delivering a cupcake.” “I don’t deliver cupcakes.” “You do tonight.”
created_at
"2026-03-18T10:43:23.27Z"
3/18/2026, 10:43:23 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
423
moderation_latency
(null)
generation_time
1372
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
66
native_tokens_completion
300
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
0.0003882
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0a213a1d9b90efa90169ba81cb54d881909ef6cf4e0fc4d115"
is_byok
false
latency
186
model_permaslug
"openai/gpt-5.4-nano-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-1773830603-wmcHUVRqBOvCzgERTNxw"
upstream_id
"resp_0a213a1d9b90efa90169ba81cb54d881909ef6cf4e0fc4d115"
total_cost
0.0003882
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
202
wordsDialogue
202
68.3860%