NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2025-04-14-01JRTSTB743W82RZBV13PQPK25
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 storm raged fiercely outside the old mansion where shadows danced beneath flickering candlelight’s trembling, eerie glow. Detective Morgan arrived just as midnight struck, sensing something ominous lurking behind the heavy wooden doors waiting. Inside the grand hall, a chilling silence enveloped the room, broken only by distant thunder crashing violently above. On the polished floor lay a lifeless body, face pale and eyes wide with frozen terror, unmoving. Clutched tightly in the victim’s hand was a mysterious note, written hurriedly in crimson ink, ominous and cryptic. The detective knelt down, carefully examining every detail, aware this was no ordinary crime scene. Suddenly, a faint sound echoed from the darkened hallway, footsteps approaching slowly, hoping to reveal hidden truths. Morgan steadied breath before calling out, voice firm and unwavering, demanding answers from the house’s restless shadows.
id
"gen-1744656215-eotsP0GpmWpBTvS8pVkz"
upstream_id
"chatcmpl-BMJ4KNusbrTYLsWNTvOhlYdtaQHUv"
total_cost
0.0003016
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:43:40.277724+00:00"
Monday, April 14th, 2025 at 6:43:40 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
555
moderation_latency
288
generation_time
3090
tokens_prompt
42
tokens_completion
177
native_tokens_prompt
42
native_tokens_completion
178
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0003016
Evaluation details
Result
Evaluator
Details
Meta Data
4.0777%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
17
1
17
2
18
3
17
4
18
5
15
6
17
7
17