NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08K9E1G3M03KM6B0MZPF7S
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.1s
Cost:
$0.000656
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
94.24%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Fog clung to Wrenhaven Manor, swallowing moonlight and good intentions. Inside, chandeliers trembled above guests who smiled too carefully. Captain Vale arrived late, carrying rain, suspicion, and a sealed letter. The host, Elias Thorne, greeted him with a bloodless grin. Music faltered when a scream split the ballroom’s polished hush. They found Lady Marrow collapsed beside the fountain, jewelry scattered. Her eyes stared upward, accusing someone among the silent guests. Captain Vale noticed one wet footprint leading toward the library. And there, on the desk, rested a knife still warm.
created_at
"2026-03-18T10:41:54.128Z"
3/18/2026, 10:41:54 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
354
moderation_latency
(null)
generation_time
1000
tokens_prompt
46
tokens_completion
160
native_tokens_prompt
41
native_tokens_completion
139
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
0.00065625
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_08eff2874912f9ac0169ba817232f881909d740969cc3dc96a"
is_byok
false
latency
241
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-1773830514-8NMm7czfhmcWwkEtYej5"
upstream_id
"resp_08eff2874912f9ac0169ba817232f881909d740969cc3dc96a"
total_cost
0.00065625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
94.24%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
10
1
9
2
11
3
10
4
10
5
10
6
10
7
10
8
10