NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSTGWZ387FACHJPK73M1T2
Run Details
Model:
GPT-4.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
2.6s
Cost:
$0.001396
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
80.33%
Matches word count
(details)
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 grandfather clock struck midnight, echoing through Rosewood Manor as shadows danced across the burgundy wallpaper like restless specters. Rain battered the stained-glass windows, obscuring the garden where a lone black cat watched intently, its paws treading silently. In the ornate dining room, seven guests clutched champagne glasses, their laughter sounding forced, eyes darting nervously to the chandelier above. A sudden crash shattered the uneasy calm, spilling silver soup tureen across the polished table and sending peacock feathers flying. Lady Winslow’s pearl necklace snapped, scattering luminous beads as she turned to find the lifeless body sprawled in the doorway. Every guest stood frozen, pulses racing, uncertain whether to scream, confess, or scrutinize each face illuminated by lightning’s harsh glare.
id
"gen-1744656221-xAJBPT8nYlOcYrvxiWAQ"
upstream_id
"chatcmpl-BMJ4Pa8ndaxj1JVl8Qt4Oa1RPcgVj"
total_cost
0.001396
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:43:44.042758+00:00"
4/14/2025, 6:43:44 PM
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
448
moderation_latency
91
generation_time
1557
tokens_prompt
42
tokens_completion
163
native_tokens_prompt
42
native_tokens_completion
164
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
0.001396
Evaluation details
Result
Evaluator
Details
Meta Data
80.33%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
19
1
19
2
21
3
20
4
20
5
20