NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A19FFND1A48VDDQ0JNWK9
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.5s
Cost:
$0.001909
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 the bakery door gave its cheerful little jingle as Nora came in from the rain, a strip of silver clinging to her umbrella. “Tell me that smell is cinnamon.” “Cinnamon, butter, and one regrettable amount of nutmeg.” Nora leaned over the glass case. “You make that sound like a confession.” “It is. I may have forgotten to label the trays before I put them in the oven.” Nora lifted a brow. “In the bakery where everyone comes in asking for the mayor’s favorite cranberry scones?” A tray thumped onto the counter. “That would be the same bakery, yes.” Outside, water tapped softly against the windows. Inside, the room glowed warm gold, all flour dust and polished wood. Nora frowned at the counter by the register, where a folded square of paper lay beneath a sugar jar. “You’ve got a note.” “I’ve had a very long morning.” Nora picked it up, careful not to smudge the ink. Her smile faded as she read it. “Well?” “It says, ‘Stop asking about the cellar.’” The baker went still, then reached for the rolling pin with unnecessary calm. “That’s interesting.” “Interesting is not the word I’d use.” “No. But it may be the word the person who wrote it would regret.” Through the rain-streaked window, a dark sedan idled at the curb, then slowly pulled away.
created_at
"2026-03-18T11:07:01.5Z"
3/18/2026, 11:07:01 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3784
moderation_latency
(null)
generation_time
3978
tokens_prompt
81
tokens_completion
501
native_tokens_prompt
67
native_tokens_completion
413
native_tokens_completion_images
0
native_tokens_reasoning
114
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
0.00190875
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_07be132bba0927570169ba87558f9481968e9081b783d06862"
is_byok
false
latency
1216
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-1773832021-hQZHcqOAHVFG3LKiV3rA"
upstream_id
"resp_07be132bba0927570169ba87558f9481968e9081b783d06862"
total_cost
0.00190875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)