NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAE5T2V9K21EEEAA5QBVVF
Run Details
Model:
GPT-5.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
25.0s
Cost:
$0.015801
Provider:
OpenAI
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 glazed the cobblestones outside Harrowgate Station as Detective Mara Quinn stepped from the train, collar already dripping with rainwater. She expected another petty theft in the sleepy town, not the uniformed constable sprinting toward her, eyes wild with panic. Breathless, he blurted that the vicar was dead inside the rectory, locked study door splintered from repeated blows last night. Mara followed him through twisting lanes, noting curtains twitching back, residents counting sirens like others might count falling stars tonight. At Saint Bartholomews gate, rainwater pooled crimson along the gravel path, thin rivulets escaping beneath the heavy oak door inside. Inside, candles guttered in the draughty nave, shadows climbing cracked stone walls like penitents ascending toward some absent salvation above. The constable pushed open the study, revealing incense haze, overturned chair, and the vicar sprawled across Persian carpet, throat ruined. Books lay scattered like startled birds, one massive Bible open beside him, its pages soaked dark where his blood gathered. Mara knelt carefully, inhaling copper and incense, her gloved fingers hovering above wounds carved with almost surgical precision and deliberation. Whoever killed Reverend Hale, she thought, understood both scripture and anatomy, and wanted their message read like a sermon aloud.
created_at
"2026-02-16T13:32:58.192653+00:00"
2/16/2026, 1:32:58 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4633
moderation_latency
(null)
generation_time
24907
tokens_prompt
46
tokens_completion
997
native_tokens_prompt
41
native_tokens_completion
1575
native_tokens_completion_images
0
native_tokens_reasoning
1290
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
0.01580125
router
(null)
provider_responses
0
id
"resp_0871de39b3db2e9d0169931c7088708193aeca32311e48ad4d"
status
200
is_byok
false
latency
162
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248752-lGtQMjcG10SJjbmUNgtb"
upstream_id
"resp_0871de39b3db2e9d0169931c7088708193aeca32311e48ad4d"
total_cost
0.01580125
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
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20