NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HKGAQ7008VVQMDKWB2673
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
3.2s
Cost:
$0.001648
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
70.49%
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 lashed the manor windows as mourners gathered below, their black umbrellas blooming like bruised flowers across the moonlit gravel. Inside, silver candles trembled beside the coffin, while whispers circled the room and grief wore faces too carefully composed. When the clock struck midnight, Lady Vale's youngest son collapsed, crimson spreading across his waistcoat like a fresh accusation. No one moved at first, except the butler, who quietly locked every door and announced that the killer remained among us.
created_at
"2026-03-06T12:22:50.974Z"
3/6/2026, 12:22:50 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
458
moderation_latency
(null)
generation_time
3123
tokens_prompt
46
tokens_completion
132
native_tokens_prompt
41
native_tokens_completion
103
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
0.0016475
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0286084b183982630169aac71b05808197ac0b05d0dfd9f4be"
is_byok
false
latency
158
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-1772799770-spf9FoCv7IEy6wzyotiB"
upstream_id
"resp_0286084b183982630169aac71b05808197ac0b05d0dfd9f4be"
total_cost
0.0016475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
70.49%
Matches word count
n/a
neededClean
false
sentences
4
wordCounts
0
20
1
19
2
19
3
21