NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKAC2SQ1NY6P6JS7VY1GNH3N
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
14.5s
Cost:
$0.013962
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 worried the manor windows while Detective Mara Vale arrived, summoned before dawn by a voice trembling through static alone. Inside, the grandfather clock coughed midnight again, though morning neared, and every servant avoided the crimson smudge on marble stairs. Lord Bellrose lay in the library, smiling faintly, a silver letter opener nestled beneath his ribs like punctuation mark itself. On the desk, seven chess pieces formed a crooked circle around spilled brandy, ash, and one perfectly polished cufflink nearby. Mara noted the locked door, the unlatched window, and the family's silence, which sounded rehearsed, devotional, almost grateful to her. Then the housekeeper whispered that Bellrose had predicted his murderer at supper, naming everyone present except himself before the storm.
created_at
"2026-03-09T22:39:30.538Z"
3/9/2026, 10:39:30 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13740
moderation_latency
(null)
generation_time
14436
tokens_prompt
46
tokens_completion
207
native_tokens_prompt
41
native_tokens_completion
924
native_tokens_completion_images
0
native_tokens_reasoning
758
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
0.0139625
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0c5c1f88288e62bc0169af4c229a6c81969711a4685fc5797b"
is_byok
false
latency
351
model_permaslug
"openai/gpt-5.4-20260305"
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-1773095970-9WcRHmPbINbpZTtLf1sx"
upstream_id
"resp_0c5c1f88288e62bc0169af4c229a6c81969711a4685fc5797b"
total_cost
0.0139625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20