NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9WDR1E6SGHD8SHCJD7ZDW
Run Details
Model:
GPT-5.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
19.6s
Cost:
$0.010901
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 hammered the abandoned seaside hotel as Detective Mara Quinn stepped from her car, clutching yesterday's unsolved case file tightly. Inside, power flickered above peeling wallpaper, revealing dust-choked chandeliers and a reception bell stained with something disturbingly dark, dried there. She followed the echo of raised voices to the ballroom, where wealthy investors awaited police clearance to reclaim their property. At the room's center lay Victor Harrow, real estate magnate, tuxedo soaked crimson, one jeweled cufflink driven into his throat. Guests clustered near overturned chairs and a shattered champagne tower, clutching glittering masks from tonight's ill-fated charity masquerade gala nervously. Near the body, a single wet footprint gleamed on parquet flooring, pointing away from open terrace doors rattling in wind. Mara watched the nervous pianist wiping his hands, though blood spatter suggested the killer had remained directly beside Victor throughout. As thunder drowned distant sirens, she realized everyone possessed airtight alibis, except the anonymous caller who insisted on remaining unseen.
created_at
"2026-02-16T13:23:11.62491+00:00"
2/16/2026, 1:23:11 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17830
moderation_latency
(null)
generation_time
19514
tokens_prompt
46
tokens_completion
291
native_tokens_prompt
41
native_tokens_completion
1085
native_tokens_completion_images
0
native_tokens_reasoning
862
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
0.01090125
router
(null)
provider_responses
0
id
"resp_026e6038cf5188500169931a2ad62481909a5d2b907af2384d"
status
200
is_byok
false
latency
154
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248170-KwtPBVK0pJH35e7HPK9E"
upstream_id
"resp_026e6038cf5188500169931a2ad62481909a5d2b907af2384d"
total_cost
0.01090125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.1633%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
21
2
20
3
20
4
21
5
20
6
20
7
20