NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM095E8GZCVPVVJ81E98BDK8
Run Details
Model:
GPT-5.4 Nano
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1.7s
Cost:
$0.000385
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
1.11%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door gave a cheerful jingle, then fell quiet under the hum of the mixer. Cinnamon and warm vanilla wrapped around the front counter, where a tray of lemon tarts cooled like bright little suns. “I can’t believe someone stole from a bake sale,”
Maribel said
, sliding a napkin across the counter. Flour dusted her cheek like a blessing. “It wasn’t the bake sale,”
Nora replied
, lifting the lid on a pastry box as if it might confess. “It was the charity donation jar. The one with the hand-painted cat on it.” Maribel leaned closer. “I watched you lock up at closing.” “Didn’t help,”
Nora said
, checking the corner of the shelf. “The jar is missing. But look.” She pointed to the empty space beside the cooling rack. A single breadcrumb trailed toward the storage door. Maribel frowned. “That’s… not from bread.” Nora’s voice softened. “No. It smells like cloves and pepper.” Maribel straightened, suddenly all business. “Someone’s been in the back. Our spice cabinet.” From behind the display cake, the oven timer clicked off with a smug little beep. Nora reached for the cabinet handle, then paused. “You think they came for the jar, but took the wrong thing?” Maribel nodded toward the tray of tarts. “Or they wanted to leave a message—and forgot to wipe their boots.”
created_at
"2026-03-18T10:51:48.89Z"
3/18/2026, 10:51:48 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
425
moderation_latency
(null)
generation_time
1574
tokens_prompt
81
tokens_completion
360
native_tokens_prompt
67
native_tokens_completion
297
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
0.00038465
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_076b1758c63a135a0169ba83c4f3948197b902c3b61a0d49df"
is_byok
false
latency
163
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-1773831108-JOTDnYNxj3BVzpPKripl"
upstream_id
"resp_076b1758c63a135a0169ba83c4f3948197b902c3b61a0d49df"
total_cost
0.00038465
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
1.11%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"Maribel said"
1
"Nora replied"
2
"Nora said"