NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A6VG4QEHF2V8TCRQ29210
Run Details
Model:
GPT-5.4 Nano (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.0s
Cost:
$0.002389
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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: Okay, Molly, no heroics. We sneak in, grab every present, and vanish before the piñata squeals. Molly: Squeals? Bill, that’s the sound of justice when kids swing plastic dinosaurs. Bill: Fine. Your plan: turn off the motion lights with your “mysterious” coin. Molly: It’s not mysterious. It’s a coin from my great-aunt’s purse, the one that definitely doesn’t electrocute people—allegedly. Bill: Allegedly is not a backup generator. Molly: Relax. I’ll tap the doorbell until it gets bored and stops recording. Bill: What about the guardian dog? Molly: He’s old. He sleeps like a decorative ottoman. Watch—he’s already dreaming of stolen bones. Bill: And the parents? Molly: We wear party hats. If anyone questions us, we say we’re with the “Magic Gift Delivery Service.” Bill: That’s a real thing? Molly: In my heart, yes. Bill: How do we carry the loot? Molly: I brought a collapsible wagon. It screams “birthday” louder than any child. Bill: Great. We’ll be the loudest thieves on Earth. Molly: Shh. Listen—laughing means the party’s inside. Bill: Then move, birthday bandit. Molly: After you, present pickpocket. Bill: Ready? If alarms chirp, we’ll sing the birthday song backwards—instant confusion, no confessions. Molly: Deal. And no fingerprints, promise.
created_at
"2026-03-18T11:10:03.794Z"
3/18/2026, 11:10:03 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18342
moderation_latency
(null)
generation_time
18728
tokens_prompt
77
tokens_completion
1003
native_tokens_prompt
66
native_tokens_completion
1901
native_tokens_completion_images
0
native_tokens_reasoning
1547
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
0.00238945
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_045b2cece92e724f0169ba880bda78819788748b34b28f75f8"
is_byok
false
latency
179
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-1773832203-ONWCKUNDy9W5RJ4i3vZY"
upstream_id
"resp_045b2cece92e724f0169ba880bda78819788748b34b28f75f8"
total_cost
0.00238945
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
0.00%
Dialogue to Total Word Ratio
Ratio: 2.93%, Deviation: 87.07%
neededClean
false
wordsTotal
205
wordsDialogue
6
49.8722%