NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAV28EBGPWTVVYZV1XC9DD
Run Details
Model:
GPT-5
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
45.0s
Cost:
$0.027851
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
Rain stitched the harbor with needles as sirens shredded midnight. The lighthouse blinked once, then watched everything without blinking again. I arrived late, pockets damp, notebook hungry for answers tonight. Police tape fluttered like jaundiced ribbons across the boarded storefront. Inside, a bell chimed after footsteps that should've been gone. The body lounged behind the counter, sprawled like careless merchandise. Blood threaded between tiles, finding drains with troubling determination below. A brass clock had stopped at twelve, hands locked together. Next to it, a postcard whispered: Wish you were elsewhere. The shopkeeper's eyes stared ceilingward, reflecting flickers from patrol cars. No shattered window, no forced door, only silence behaving politely. Yet perfume drifted almond-sweet, a warning dressed like dessert tonight. Neighbors clustered outside, their umbrellas grazing like uncertain sea creatures. Someone whispered arsenic, and everyone immediately stopped whispering altogether there. I noted smudged ledgers, empty tracks, and missing frames everywhere. The register mouthed zeros, as though yesterday had never paid. On the threshold lay salt, arranged carefully into curling symbols. I photographed everything, while the harbor kept wettening the world. Then a gull screamed, and somewhere inside, a latch answered. Whoever left remained here, hiding behind certainty and careful timing. I closed my notebook, opened my eyes, and knocked politely. Murder, I thought, prefers company almost as much as shadows.
created_at
"2026-02-16T13:40:20.492929+00:00"
2/16/2026, 1:40:20 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4227
moderation_latency
(null)
generation_time
44630
tokens_prompt
46
tokens_completion
1179
native_tokens_prompt
41
native_tokens_completion
2780
native_tokens_completion_images
0
native_tokens_reasoning
2432
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
0.02785125
router
(null)
provider_responses
0
id
"resp_09144c77a091cddc0169931e16ecb48194a70ca3f1d27de548"
status
200
is_byok
false
latency
203
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771249174-b09NBbyIKhRcXYObxMog"
upstream_id
"resp_09144c77a091cddc0169931e16ecb48194a70ca3f1d27de548"
total_cost
0.02785125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
98.8219%
Matches word count
n/a
neededClean
false
sentences
22
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10
10
10
11
11
12
10
13
10
14
10
15
10
16
10
17
10
18
10
19
10
20
10
21
10