NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HXPW8ZXDVRAMSE8GSB9W5
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.3s
Cost:
$0.002128
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
59.10%
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, pretending grief, hiding calculations, and watching the grandfather clock refuse midnight. When Lady Haverford collapsed beside the champagne fountain, nobody screamed immediately; surprise lingered first, sharp as cut crystal. Inspector Vale arrived through the storm, noting muddy footprints, extinguished candles, and one silver cufflink glinting beneath velvet drapery. Upstairs, a locked music room concealed discordant violin notes, while downstairs every guest rehearsed alibis with suspiciously careful breathing. Vale studied their faces and saw something worse than panic: relief, quickly masked behind condolences, trembling hands, and lies.
created_at
"2026-03-06T12:28:25.36Z"
3/6/2026, 12:28:25 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
441
moderation_latency
(null)
generation_time
4277
tokens_prompt
46
tokens_completion
182
native_tokens_prompt
41
native_tokens_completion
135
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
0.0021275
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_066b3d4513fe64800169aac8696b60819681645edb23544a20"
is_byok
false
latency
171
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-1772800105-ZZisg7D8EOMuXDqBMCri"
upstream_id
"resp_066b3d4513fe64800169aac8696b60819681645edb23544a20"
total_cost
0.0021275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
59.10%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
18
2
19
3
19
4
19