NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AE43VHEQ71RR4DTKBM8M3
Run Details
Model:
GPT-5.4 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
2.5s
Cost:
$0.000249
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
3.94%
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
The rain tapped quietly outside Marrowick House as guests gathered for winter dinner, unaware of tonight's missing heirloom. Beneath gaslit ceilings, Detective Elara Voss watched servants hurry, noting every whisper, every glance, every trembling hand tonight. Sir Alden’s portrait still hung above the fireplace, while his signet ring vanished from the display case. When guests laughed too loudly, Elara asked for silence, then examined footprints leading from study to cellar. Mrs. Harrow, trembling in lace, swore she last saw the ring near midnight, before storm swallowed lanterns. From the cellar stair, a faint smell of almonds rose, promising poison, or simply unfamiliar perfume tonight. Elara found a torn glove by the stone steps, stitched with initials matching none of them. The butler insisted doors stayed locked, yet a keyhole scrape gleamed, fresh as yesterday’s secrets.
created_at
"2026-03-18T11:14:01.99Z"
3/18/2026, 11:14:01 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
433
moderation_latency
(null)
generation_time
2425
tokens_prompt
46
tokens_completion
233
native_tokens_prompt
41
native_tokens_completion
193
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
0.00024945
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0bb102490cded0ba0169ba88fa0be08197b3f9340fcb5c7457"
is_byok
false
latency
171
model_permaslug
"openai/gpt-5.4-nano-20260317"
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-1773832441-PWb9TxB02uyutkcnlW9h"
upstream_id
"resp_0bb102490cded0ba0169ba88fa0be08197b3f9340fcb5c7457"
total_cost
0.00024945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
3.94%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
18
1
18
2
17
3
17
4
17
5
17
6
16
7
15