NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GVEVP9729N2RZMQZC0HFP
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
5.0s
Cost:
$0.002037
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
84.45%
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
Rain glazed Blackthorn Manor as mourners gathered beneath iron skies. Inside, candles trembled, painting long shadows across ancestral portraits. Lady Wren greeted guests with smiles brittle as winter glass. At midnight, the clock groaned, and someone screamed upstairs suddenly. They found Lord Ashcombe sprawled beside shattered decanter shards there. Blood darkened the Persian rug like spilled sacramental wine. His signet ring was missing, though windows remained latched. No servant admitted hearing footsteps, yet mud marked corridors. Detective Hale arrived before dawn, carrying silence like judgment. He studied every face, and one face studied back.
created_at
"2026-03-06T12:09:43.037Z"
3/6/2026, 12:09:43 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
451
moderation_latency
(null)
generation_time
4946
tokens_prompt
46
tokens_completion
172
native_tokens_prompt
41
native_tokens_completion
129
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
0.0020375
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0dc0665eb363fee40169aac40717cc8197aa6a22e086f43194"
is_byok
false
latency
186
model_permaslug
"openai/gpt-5.4-20260305"
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-1772798983-KjcAUOw2reJiONhyhY68"
upstream_id
"resp_0dc0665eb363fee40169aac40717cc8197aa6a22e086f43194"
total_cost
0.0020375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
84.45%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
9
2
10
3
10
4
10
5
9
6
9
7
9
8
9
9
9