NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07Z17XK0Z1549BZ92J0VP2
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.1s
Cost:
$0.001827
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9576%
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: “No alarms. We’re here for presents, not karma.” Bill: “Great, because my karma’s on vacation.” Molly: “Shh—those party favors are louder than your shoes.” Bill: “My shoes are innocent. They just want to be invited.” Molly: “Plan A: slide through the door while the clown says ‘Ta-da!’ Plan B: borrow the piñata’s rope as a grappling line.” Bill: “Do we need the grappling line if we walk in like two extremely underdressed uncles?” Molly: “Only if you can stop the squeaky propeller keychain.” Bill: “It’s not propeller—it’s morale.” Molly: “Morale doesn’t squeak.” Bill: “It does when you’re nervous.” Molly: “I’m not nervous. I’m… professionally excited.” Bill: “Your eyebrows are sprinting.” Molly: “Focus. We steal every present, even the weird ones labeled ‘from Grandma.’” Bill: “What if Grandma made those time-travel socks again?” Molly: “Then we steal them and pretend we never met.” Bill: “Okay, but how do we open the gift pile without looking like we’re stealing it?” Molly: “We simply admire it aggressively. Kids love aggression.” Bill: “Kids love us?” Molly: “Only if we look like Santa’s accountants.” Bill: “I can do accountant.” Molly: “Perfect. On my count—three… two… one. Go, Bill—try not to squeak this time.”
created_at
"2026-03-18T10:30:50.379Z"
3/18/2026, 10:30:50 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15519
moderation_latency
(null)
generation_time
15887
tokens_prompt
77
tokens_completion
958
native_tokens_prompt
66
native_tokens_completion
1451
native_tokens_completion_images
0
native_tokens_reasoning
1122
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
0.00182695
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0e27c6aee6ba6b290169ba7eda784c8190bd5b798b38c4dae5"
is_byok
false
latency
207
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-1773829850-w65gDFyxVDN1iGI8qfUw"
upstream_id
"resp_0e27c6aee6ba6b290169ba7eda784c8190bd5b798b38c4dae5"
total_cost
0.00182695
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 89.22%, Deviation: 0.78%
neededClean
false
wordsTotal
204
wordsDialogue
182
99.9576%