NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09WK4EFAEHA8A46YJD90RM
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.4s
Cost:
$0.002021
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.65%
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 Maple Street Bakery gave a cheerful jingle as Nora slid a tray of cinnamon twists into the display case. Outside, the town square was already dusted with snow, and inside, the windows fogged pleasantly from the warmth of yeast and sugar. “You’ve got a full house before nine.” “That’s what happens when Mrs. Bell announces a pie sale and forgets to mention the part where half the town shows up.” Mara laughed and tucked her scarf under one arm. “Any luck with the missing recipe book?” Nora’s hands stilled on the glass. “Still missing.” “Odd, that.” “Odd isn’t the word I’d use for a cookbook vanishing from a locked office the same night Mr. Pritchard’s antique spoon disappeared.” Mara leaned closer to the counter. “You think they’re connected?” “I think someone wanted people looking in the wrong drawer.” A burst of flour drifted from the kitchen, and both of them turned. Old Mr. Haskins stood in the doorway, white as powdered sugar, clutching a paper bag. “I found this behind the flour sacks,”
he said
, setting it down with a thump. “And I don’t believe it belongs to the bakery.” Nora peeled back the folded paper and went very still. “Mara.” “What is it?” “A train ticket. To Cedar Ridge. Dated last night.”
created_at
"2026-03-18T11:04:27.547Z"
3/18/2026, 11:04:27 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2699
moderation_latency
(null)
generation_time
3052
tokens_prompt
81
tokens_completion
475
native_tokens_prompt
67
native_tokens_completion
438
native_tokens_completion_images
0
native_tokens_reasoning
146
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
0.00202125
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0acc8093e86d753b0169ba86bb9e5c8195a8e41af62d29c617"
is_byok
false
latency
212
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-1773831867-SThOSDssAmp37Bdo5FgV"
upstream_id
"resp_0acc8093e86d753b0169ba86bb9e5c8195a8e41af62d29c617"
total_cost
0.00202125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"he said"