NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAKTNMSXJQGQHRE7ZAZ3TF
Run Details
Model:
GPT-5 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
32.2s
Cost:
$0.006852
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
Thunder rattled the attic window as the gardener discovered a hand in the rosebush under moonlight's thin wash of blood. Neighbors gathered at iron gates, whispering names like confessions while detectives sealed the lane and photographed muddy footprints with care. Inside the manor's parlor, a shattered crystal decanter glowed beside a body draped over antique carpet and wilted lilies sadly. Her fingers curled around a theater ticket, mouthing unreadable words, as if rehearsing an alibi from beyond in faded ink. Detective Marlowe, trench coat dripping rain, lit a cigarette and watched candlelight tremble across the victim's still, pale face lonely. An envelope lay at her side, stamped with a crimson seal and scrawled letters that spelled only one word: betrayal. The butler's hands trembled as he admitted hearing muffled arguments around midnight, laughter laced with something like menace and denial. Outside, a stray dog nosed at a crimson smear on the lane, snuffling evidence neither human courage nor conscience could. Rain stitched the night into darker seams while the county coroner arrived with gloved hands and solemn, precise movements again. Murmurs folded into the wallpaper's faded pattern, gossip arranging itself into motives, alibis, and ancient grudges rekindled tonight like tinder. Marlowe closed his eyes briefly, imagining every suspect's small, secret life turning suddenly monstrous under police lights and public shame.
created_at
"2026-02-16T13:36:10.674308+00:00"
2/16/2026, 1:36:10 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2548
moderation_latency
(null)
generation_time
32056
tokens_prompt
46
tokens_completion
1077
native_tokens_prompt
41
native_tokens_completion
3421
native_tokens_completion_images
0
native_tokens_reasoning
3072
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
0.00685225
router
(null)
provider_responses
0
id
"resp_0218388a87fa72620169931d29bf0c81969a9044dfb87c1793"
status
200
is_byok
false
latency
136
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248937-AtdruCuRVm0nUKOT9N2y"
upstream_id
"resp_0218388a87fa72620169931d29bf0c81969a9044dfb87c1793"
total_cost
0.00685225
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
11
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20
10
20