NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0875AW30RFHTAJ7VHPR541
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.5s
Cost:
$0.000769
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
70.22%
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
Rain polished the station windows, turning morning commuters into blurred silhouettes, while Inspector Vale studied the body beneath the clock. The victim, a watchmaker named Adrian Quill, lay beside scattered gears, his throat marked by a precise, almost theatrical wound. No one had heard a scream, though every clerk claimed to notice the station’s bells stop exactly at seven-twelve. Vale knelt, observing a smear of crimson on Quill’s cuff, and found a folded ticket tucked inside the dead man’s pocket. It read, in trembling ink, Platform Three, Midnight Appointment, and beneath that, a single word: Beware. Above them, the clock resumed ticking, as if awakened, and the entire waiting room seemed to inhale with quiet dread.
created_at
"2026-03-18T10:35:16.714Z"
3/18/2026, 10:35:16 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
427
moderation_latency
(null)
generation_time
1389
tokens_prompt
46
tokens_completion
192
native_tokens_prompt
41
native_tokens_completion
164
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.00076875
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0c3b93d0ddce3a8e0169ba7fe4c8e48196981b475259bf1748"
is_byok
false
latency
189
model_permaslug
"openai/gpt-5.4-mini-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773830116-svDXe2gXhWbd7kjRxO9t"
upstream_id
"resp_0c3b93d0ddce3a8e0169ba7fe4c8e48196981b475259bf1748"
total_cost
0.00076875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
70.22%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
20
2
19
3
21
4
16
5
20