NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKABYY6BBMJ8HSCGZFPHMMER
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
14.1s
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 windows of Blackthorn Hall as Inspector Vale arrived, carrying a damp overcoat and news nobody expected tonight. Inside, the birthday guests stood frozen beneath glittering chandeliers, surrounding Sir Alistair's body like mourners rehearsing guilt for the police. A violin still hummed from the gallery above, its final note trembling longer than the scream that summoned everyone downstairs. No blood stained the marble floor, yet a silver dessert fork protruded from his throat with deliberate, obscene elegance there. Lady Beatrice clutched her pearls, the butler avoided eye contact, and the heir smiled briefly before remembering sorrow properly now. Vale removed his gloves, studied the clock stopped at nine, and wondered who had silenced it before dinner was served. On the mantel, seven wax candles burned evenly, although one chair was empty and one place setting remained untouched tonight. When thunder rolled overhead, Vale announced the doors were locked, and every face revealed relief before fear reclaimed it again.
created_at
"2026-03-09T22:37:24.054Z"
3/9/2026, 10:37:24 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13601
moderation_latency
(null)
generation_time
13788
tokens_prompt
46
tokens_completion
650
native_tokens_prompt
41
native_tokens_completion
924
native_tokens_completion_images
0
native_tokens_reasoning
713
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_0e0c4db448034fd20169af4ba41f548197b6694e551d455903"
is_byok
false
latency
168
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-1773095844-eBn5VDbtedpUdePyGGYt"
upstream_id
"resp_0e0c4db448034fd20169af4ba41f548197b6694e551d455903"
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
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20