NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A6G5B1ZDC0TTMJ3JEDHYT
Run Details
Model:
GPT-5.4 Nano (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
35.0s
Cost:
$0.007386
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 and Bill slid under the crepe-paper table, listening to squeals and the thump of party games. The room smelled of frosting and bubble bath, which somehow made Bill feel brave. Molly traced the present pile on a napkin, whispering cues between bites of stolen licorice. Bill kept checking his wristwatch like it might ring up permission. Outside, a clown rehearsed jokes, and every laugh echoed through their hideout. When the music paused, Molly nodded toward the gift stack and prepared her heist speech. She raised a gloved finger, and Bill adjusted the ribbon cutter with theatrical menace for them. “Muffle your sneezes, Bill; kids hate surprises.” “Too late, I already auditioned as a mascot.” “Good. Now we borrow presents, not hearts.” “Their wrapping is basically armor.” “Armor doesn’t work on my stealthy cat mask.” “It’s smiling, so security laughs and opens doors.” “If anyone asks, we’re party consultants.” “I’ll consult on loot logistics, legally adjacent.” “Remember, no grabbing from the toddlers’ table.” “Then we’ll only steal the big boxes; that’s fair.” “See the banner? ‘Happy Birthday, Eli!’ I’m studying their target.” “Lucky Eli, I’m Bill; I’m basically family.” “Great, our getaway is your garage, where toys go to thrive.”
created_at
"2026-03-18T11:09:52.185Z"
3/18/2026, 11:09:52 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
34284
moderation_latency
(null)
generation_time
34853
tokens_prompt
77
tokens_completion
1500
native_tokens_prompt
66
native_tokens_completion
5898
native_tokens_completion_images
0
native_tokens_reasoning
5605
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
0.0073857
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_02e800e8d5738e7a0169ba88003cbc819584d3135342b2ddaf"
is_byok
false
latency
182
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-1773832192-6GMimRDmPyqelVkjriTt"
upstream_id
"resp_02e800e8d5738e7a0169ba88003cbc819584d3135342b2ddaf"
total_cost
0.0073857
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
100.00%
Dialogue to Total Word Ratio
Ratio: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
100
100.0000%