NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9Y3RVT62M9MR2DZTQFRDC
Run Details
Model:
GPT-5.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
27.6s
Cost:
$0.019091
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 smeared the city lights into trembling ribbons as Detective Maris Crowe reached the cordoned alley, coat dripping with rainwater. Uniformed officers clustered near the dumpster, trading hushed theories, but conversation thinned when they noticed Maris approaching through the downpour. The alley smelled of rot and metal, a sour cocktail swirling beneath siren wails and the distant grind of traffic. Beneath the yellow tarp lay the body, outlined by fallen trash and glass, like the alley itself rejected him tonight. Maris crouched beside the tarp, water seeping into her boots, and lifted the edge, bracing for another ordinary nightmare unfolding. The victim's face stared upward, eyes filmed with rain, expression peaceful except for the dark crescent carved across his throat. Silver glinted against his palm, a small chess knight clenched so tightly the edges had punctured skin despite the rigor. Maris exchanged a glance with Sergeant Hale, whose jaw flexed once, betraying recognition before his features settled into professional blankness. We had a message last week, anonymous, about a game beginning, Hale muttered, and nobody listened because nothing happened then. Raindrops gathered in the dead man's hollowed ear, ticking like seconds, while somewhere unseen the first move waited, smiling patiently.
created_at
"2026-02-16T13:24:14.052377+00:00"
2/16/2026, 1:24:14 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4244
moderation_latency
(null)
generation_time
27353
tokens_prompt
46
tokens_completion
1066
native_tokens_prompt
41
native_tokens_completion
1904
native_tokens_completion_images
0
native_tokens_reasoning
1627
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
0.01909125
router
(null)
provider_responses
0
id
"resp_062d58afe587fa910169931a6228ec8194aa3b67c2e23f946a"
status
200
is_byok
false
latency
193
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248226-5JTI6FBs7p6BdmlGhOpg"
upstream_id
"resp_062d58afe587fa910169931a6228ec8194aa3b67c2e23f946a"
total_cost
0.01909125
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