NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09K7QPMK67E23FDT7XXS4V
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
6.7s
Cost:
$0.007055
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain stitched the mansion windows as Detective Mara Vale stepped inside, carrying a notebook, a flashlight, and a growing dread. The chandelier flickered above the ballroom, where guests whispered around a body on the marble floor, untouched except for blood. No one had heard the shot, yet the victim's pocket watch lay open, stopped at exactly midnight, and smeared red. Mara crouched beside him, noticing three wet footprints leading toward the library, each one smaller than the last, despite everything. She followed them anyway, and when the library door creaked open, someone already knew her name from the darkness inside.
created_at
"2026-03-18T10:59:20.965Z"
3/18/2026, 10:59:20 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6443
moderation_latency
(null)
generation_time
6555
tokens_prompt
46
tokens_completion
283
native_tokens_prompt
41
native_tokens_completion
1561
native_tokens_completion_images
0
native_tokens_reasoning
1427
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
0.00705525
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ee97b98f59848960169ba8589057081949cc904ae87618ff2"
is_byok
false
latency
173
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-1773831560-y4ja8zuQCWCOgMENxpAD"
upstream_id
"resp_0ee97b98f59848960169ba8589057081949cc904ae87618ff2"
total_cost
0.00705525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
20
2
20
3
20
4
20