NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKART513Y8PSBAD3K56R9MW
Run Details
Model:
GPT-5.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
17.7s
Cost:
$0.013651
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 railway station as Detective Mara Ivers stepped from her car, collar up against November wind tonight. The call had promised routine trespassing, yet the waiting paramedics would not meet her eyes under flickering lights this evening. Inside the ticket hall, echoes of dripping water mingled with distant thunder, swallowing her footsteps like something listening in darkness. On the cracked tiles lay a man in evening dress, throat opened carefully, blood arranged in deliberate, almost artistic circles. His left hand pointed toward the shuttered ticket window, where someone had written three letters in blood, trembling but purposeful. Mara noted the cooled skin, the missing wallet, the unscuffed shoes, building a timeline that refused to make sense tonight. Outside, the storm strengthened, rattling loose panes and drowning traffic, isolating the station like an island nobody remembered owning anymore. She crouched beside the body and smelled not only iron and damp wool, but faintly, clinging insistently, expensive gardenias nearby. That fragrance dragged memory from childhood funerals, when her grandmother whispered that murderers always choose perfumes they secretly despised wearing. Before Mara could question the paramedics, the station clocks simultaneously chimed midnight, though her watch insisted it was still eleven.
created_at
"2026-02-16T13:38:39.442702+00:00"
2/16/2026, 1:38:39 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3832
moderation_latency
(null)
generation_time
17069
tokens_prompt
46
tokens_completion
1005
native_tokens_prompt
41
native_tokens_completion
1360
native_tokens_completion_images
0
native_tokens_reasoning
1093
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
0.01365125
router
(null)
provider_responses
0
id
"resp_071eda84a7f46f4f0169931dcd085081949fb36c80fa502e7a"
status
200
is_byok
false
latency
167
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771249100-jtcdT3yiHugMS0oMkk6e"
upstream_id
"resp_071eda84a7f46f4f0169931dcd085081949fb36c80fa502e7a"
total_cost
0.01365125
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