NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSXDXHRX4Z5742MQY9HNXM
Run Details
Model:
GPT-4.1 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.7s
Cost:
$0.000087
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
57.16%
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 fog crept through the silent streets as Detective Harris arrived at the crime scene, eyes scanning every shadow carefully. A single flickering lantern illuminated the alley, revealing a body sprawled awkwardly beneath a broken wooden crate. Nearby, shattered glass and discarded papers told a story of chaos, struggle, and hurried escape before the murderer's departure. Askew, the victim's face betrayed fear and pain, as blood pooled around him, slick and dark beneath the dim streetlamp glow. Clues lay scattered—an overturned chair, a torn piece of fabric, footsteps leading away into the shadows, silent witnesses to violence. Inside the nearby building, faint screams echoed, hinting at secrets perhaps better left hidden, waiting for discovery by keen eyes. Detective Harris knelt, examining footprints and blood splatters, knowing each detail would weave together the puzzle's tragic narrative. The night air grew colder as whispers of suspicion spread among neighbors, each with stories, fears, secrets buried deep inside themselves.
id
"gen-1744656316-RuTWTRQyEeKgngVs8KOY"
upstream_id
"chatcmpl-BMJ5xVj3EwHYGXOPHQk6iVbTxOURL"
total_cost
0.0000874
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:18.464813+00:00"
4/14/2025, 6:45:18 PM
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
238
moderation_latency
169
generation_time
492
tokens_prompt
42
tokens_completion
207
native_tokens_prompt
42
native_tokens_completion
208
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
0.0000874
Evaluation details
Result
Evaluator
Details
Meta Data
57.16%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
17
2
19
3
21
4
21
5
20
6
18
7
21