NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSR5VNTXMTBJXX6SN4R45K
Run Details
Model:
GPT-4.1 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
2.0s
Cost:
$0.000097
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
58.93%
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
In the dimly lit study, Professor Adler's body lay sprawled across antique Persian rugs, a crimson pool soaking into worn silk. A single candlestick toppled nearby, its melted wax shimmering under the flickering flame, casting eerie shadows on dusty, ancient books. Detective Morgan arrived silently, surveying the scene with keen eyes, noting the ornate dagger lodged in the victim’s back, blood still fresh. Outside the grand estate, heavy fog clung to the mansion, muffling footsteps and whispers of gossip from suspicious neighbors nearby. Inside, the air was thick with tension, secrets lurking behind polished furniture and antique portraits staring with silent judgment. A broken window latch suggested forced entry, yet nothing appeared stolen, and the room’s contents remained untouched and orderly. Morgan carefully examined the dagger, noticing strange symbols etched onto its hilt, hinting at an obscure, perhaps personal, motive. Footsteps echoed in the corridor, revealing several people, each with anxious expressions and motives concealed behind calm facades. How many lies had been told before tragedy struck, and who among these faces carried the truth buried within?
id
"gen-1744656144-TEEE4qVytQ4WN7sRnP5M"
upstream_id
"chatcmpl-BMJ3BW9vWQZt3V4zxL1L2ZFAxkOgY"
total_cost
0.0000966
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:42:26.720458+00:00"
4/14/2025, 6:42:26 PM
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
395
moderation_latency
93
generation_time
759
tokens_prompt
42
tokens_completion
230
native_tokens_prompt
42
native_tokens_completion
231
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
0.0000966
Evaluation details
Result
Evaluator
Details
Meta Data
58.93%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
21
1
20
2
22
3
20
4
19
5
19
6
19
7
18
8
19