NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09PHN71BJ65FB016ZPM8DW
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.0s
Cost:
$0.001661
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
13.53%
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 over Dewdrop Bakery gave a cheerful jingle as Mara pushed the door open, and the warm smell of cinnamon, butter, and rising bread wrapped around her like a quilt. “You’re late,”
said Ellery
, sliding a tray of thumbprint cookies onto the cooling rack. “I was investigating.” Ellery arched one brow. “That sounds ominous for a Tuesday.” “It is when Mrs. Pritchard’s prize rose bush is missing and the only clue is a muddy footprint by the gazebo.” “Good heavens.” Ellery wiped flour from her hands. “Did you find the bush?” “Not yet. But I did find a wheelbarrow track behind the florist’s shop, and Deputy Cole thinks it may connect to the greenhouse break-in.” Ellery handed her a lemon tart. “You say that like it’s perfectly ordinary.” “In Briar Creek? It practically is.” From the front counter came a soft cough. Old Mr. Bell was pretending not to listen while selecting a scone. Ellery lowered her voice. “And are you here for sleuthing, or because you skipped lunch again?” “Both.” “Then sit down before you faint and scare my customers.” Mara took a bite of tart and sighed. “If every mystery came with this much lemon glaze, I’d solve twice as many.” Ellery smiled, but her eyes flicked toward the window. “Unless,”
she said quietly
, “the thief comes in for pastries too.”
created_at
"2026-03-18T11:01:09.429Z"
3/18/2026, 11:01:09 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2325
moderation_latency
(null)
generation_time
2689
tokens_prompt
81
tokens_completion
495
native_tokens_prompt
67
native_tokens_completion
358
native_tokens_completion_images
0
native_tokens_reasoning
51
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
0.00166125
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_09376925249ba7a70169ba85f57edc8195a23ada97b16bf242"
is_byok
false
latency
213
model_permaslug
"openai/gpt-5.4-mini-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-1773831669-J27BFkAbr2A9I1cGb25W"
upstream_id
"resp_09376925249ba7a70169ba85f57edc8195a23ada97b16bf242"
total_cost
0.00166125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"said Ellery"
1
"she said quietly"