NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAE4KHXQJHKYMECH6ASJ71
Run Details
Model:
GPT-5.2
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
18.5s
Cost:
$0.011160
Provider:
OpenAI
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 Harrow Street as midnight bells faded away. Detective Mara Quinn watched the townhouse window glow faintly inside. A scream snapped through silence, then cut off abruptly tonight. Neighbors opened curtains, but nobody stepped onto wet cobblestones yet. Mara climbed the stoop, smelling lilacs and something metallic nearby. The brass knocker hung ajar, like a broken jawbone still. Inside, candles guttered, painting walls with nervous, wavering shadows alone. On the carpet lay Lionel Graves, banker, philanthropist, newly dead. His right hand gripped a torn note stained by ink. Mara read one word: 'Tuesday,' and felt the trap closing.
created_at
"2026-02-16T13:32:50.488637+00:00"
2/16/2026, 1:32:50 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5832
moderation_latency
(null)
generation_time
18335
tokens_prompt
46
tokens_completion
605
native_tokens_prompt
41
native_tokens_completion
792
native_tokens_completion_images
0
native_tokens_reasoning
637
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
0.01115975
router
(null)
provider_responses
0
id
"resp_04f13aca9b9447f40169931c6f5440819097a1e6485d22aba1"
status
200
is_byok
false
latency
195
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771248751-4pcCM0sYlNbdUHQSi7Ip"
upstream_id
"resp_04f13aca9b9447f40169931c6f5440819097a1e6485d22aba1"
total_cost
0.01115975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10