NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GAMWH8AQR9K9SPK8C1RPH
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.3s
Cost:
$0.003778
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
23.17%
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 hammered Blackthorn Hall as mourners gathered, their umbrellas trembling beneath a sky bruised purple by the approaching midnight storm. Inside, the grandfather clock struck twelve, and every portrait seemed to flinch while candlelight crawled over polished walnut walls. Lady Wren Ashcombe smiled too brightly at dinner, raising her crystal glass moments before collapsing across the linen. No one moved at first; then screams rose sharp and sudden, drowning the violin and silencing the servants. Detective Elias Vale, uninvited but nearby, stepped from the vestibule shadows, already counting faces, lies, and half-finished toasts. Upon the silver tray beside Lady Wren's limp hand rested a foxglove blossom, wet with spilled burgundy. The guests exchanged brittle glances, because everyone knew the conservatory had been locked since the gardener's funeral. Vale bent close, studying her lips, then the room, where grief mingled uneasily with calculation, fear, and opportunity. Outside, thunder rolled again, sealing Blackthorn Hall from the world, while somewhere upstairs a door clicked softly. By dawn, one of them would confess nothing, another would disappear, and the dead woman would keep accusing.
created_at
"2026-03-06T12:00:32.397Z"
3/6/2026, 12:00:32 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
433
moderation_latency
(null)
generation_time
8955
tokens_prompt
46
tokens_completion
311
native_tokens_prompt
41
native_tokens_completion
245
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
0.0037775
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_051d6a29997bbc760169aac1e093b48195b7d1293b16e6f6ce"
is_byok
false
latency
186
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-1772798432-BTvJmTha9mLcS7N3XyxA"
upstream_id
"resp_051d6a29997bbc760169aac1e093b48195b7d1293b16e6f6ce"
total_cost
0.0037775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
23.17%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
19
2
18
3
18
4
18
5
17
6
17
7
18
8
17
9
18