NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07A3YKKJARRPKFRZN8F94E
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.5s
Cost:
$0.000908
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
77.52%
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 manor windows closed, while lanterns trembled along the corridor, where tonight's guests smiled too carefully at one another. Detective Mara Vale arrived after midnight, carrying a damp coat, a keen stare, and the memory of three unsolved disappearances. In the library, Lord Ashcombe lay sprawled beside the hearth, his silver letter opener pinned beneath a single, deliberate wound. No one had touched the body, yet every guest possessed bloodshot eyes, trembling hands, and an alibi spoken far too quickly. Mara noticed the clock had stopped at eleven seventeen, exactly when the storm outside drowned every sound from the west wing. A maid whispered that the lord had summoned someone privately, and that afterward she heard glass breaking and a woman crying. As Mara studied the room, she found one wet footprint, one missing portrait, and one note reading, You are next.
created_at
"2026-03-18T10:19:25.023Z"
3/18/2026, 10:19:25 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
401
moderation_latency
(null)
generation_time
1394
tokens_prompt
46
tokens_completion
231
native_tokens_prompt
41
native_tokens_completion
195
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
0.00090825
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_02e06068f433cb240169ba7c2d12e08190a1a27861f8e3f958"
is_byok
false
latency
168
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-1773829165-CUHtUtp9WwIspSVgZq8F"
upstream_id
"resp_02e06068f433cb240169ba7c2d12e08190a1a27861f8e3f958"
total_cost
0.00090825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
77.52%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
21
1
20
2
20
3
21
4
21
5
21
6
20