NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1JCMGYHGDKSQM05JQMYSFG
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.2s
Cost:
$0.001948
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
66.97%
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
At dusk, the manor breathed quietly, windows glowing amber while rain stitched silver threads across the sleeping, watchful gardens below. Guests gathered in the drawing room, smiling too brightly, their laughter brittle as glass beneath the grandfather clock's measured accusations. When Lady Vale raised her crystal goblet for silence, thunder answered first, and someone unseen extinguished every candle instantly. Darkness swallowed the room completely; then came a gasp, a crash, and one terrible note from the violin. Lightning revealed Lady Vale collapsed beside the hearth, scarlet blooming through silk, while every guest stared at someone else.
created_at
"2026-03-06T12:36:34.471Z"
3/6/2026, 12:36:34 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
461
moderation_latency
(null)
generation_time
4180
tokens_prompt
46
tokens_completion
167
native_tokens_prompt
41
native_tokens_completion
123
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
0.0019475
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_01d828ec70a41f9d0169aaca5287588193b80b415e7e04e3da"
is_byok
false
latency
150
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-1772800594-Xq1GAnyL3nYWQ50gY0g6"
upstream_id
"resp_01d828ec70a41f9d0169aaca5287588193b80b415e7e04e3da"
total_cost
0.0019475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
66.97%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
20
2
19
3
18
4
19