NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9GD8Z7Z2DZ91BTR4TFPX3
Run Details
Model:
GPT-5 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
40.5s
Cost:
$0.001549
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
The rain painted the town's narrow streets with glassy echoes as evening settled over the deserted harbor upon the quay. A lone lamplight flickered near the bakery, casting hesitant shadows across puddles while distant thunder memorized every crime that night. At the harbor warehouse, a crate lay open, its splintered lid revealing a pallid hand faintly gloved beneath a hush. The victim wore a burgundy scarf, knotted loosely, as if last evening's kiss still clung to a memory for someone. I arrived with damp shoes and a notebook, knowing every answered question births another riddle around here tonight somewhere listening. The town clock sighed, twelve strokes mourning someone, while witnesses whispered names that did not fit the map that night. A cigarette butt curled near the crate smelled of rain and factory ash, secretly guarding a cipher’s first breath tonight. The harbor whispered of secrets, and every gull's cry sounded like a question no one wished answered on that night.
created_at
"2026-02-16T13:16:57.898036+00:00"
2/16/2026, 1:16:57 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2256
moderation_latency
(null)
generation_time
39892
tokens_prompt
46
tokens_completion
1291
native_tokens_prompt
41
native_tokens_completion
3867
native_tokens_completion_images
0
native_tokens_reasoning
3648
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
0.00154885
router
(null)
provider_responses
0
id
"resp_01cdb25afde6e67001699318a1234081959c444f4b7cac6e69"
status
200
is_byok
false
latency
109
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771247777-6DJEVYo8ArZEetjJchlU"
upstream_id
"resp_01cdb25afde6e67001699318a1234081959c444f4b7cac6e69"
total_cost
0.00154885
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
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20