NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKAC3T4PZWWVA8JV4KAY30ZB
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
16.3s
Cost:
$0.015447
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 polished the manor windows while mourners gathered below, whispering through black veils as midnight settled over the family crypt. When the clock struck twelve, Lady Verity Ashcombe descended the staircase smiling faintly, one gloved hand closed around a telegram. No one noticed the butler freezing beside the portrait gallery, except me, because I had already seen the blood there. It streaked the marble banister like a signature, fresh and bright, ending beneath the matriarch's locked bedroom door upstairs tonight. Before anyone screamed, the lights failed, and somewhere above us a woman laughed once, sharply, then stopped forever in darkness. By the time candles arrived, Lady Verity lay dead beside the telegram, and every face in the hall had changed. The message, still clutched between her fingers, contained seven words only: I know what happened there that night last summer. I introduced myself to the inspector then, though privately I feared his questions less than the answers waiting upstairs alone.
created_at
"2026-03-09T22:40:03.742Z"
3/9/2026, 10:40:03 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14444
moderation_latency
(null)
generation_time
16159
tokens_prompt
46
tokens_completion
262
native_tokens_prompt
41
native_tokens_completion
1023
native_tokens_completion_images
0
native_tokens_reasoning
816
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
0.0154475
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_081d2ada962352bf0169af4c43cc888194a5b5881eb99c4008"
is_byok
false
latency
141
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-1773096003-3OgdrF8umx19y0ZFwj1A"
upstream_id
"resp_081d2ada962352bf0169af4c43cc888194a5b5881eb99c4008"
total_cost
0.0154475
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