NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AKZAS9EJFNE0X3CNHTSJV
Run Details
Model:
GPT-5.4 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.5s
Cost:
$0.000266
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
3.38%
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 tapped the courthouse windows as Detective Mara Ellery studied a corpse beneath gaslight, silent courtroom murmurs fading. A judge requested immediate answers, claiming the victim vanished nightly from his chambers, then returned dead at dawn. On the marble floor, a torn glove lay beside a ticking pocket watch, stopped precisely at 3:17. Witnesses swore he argued with Councilman Varric yesterday, then laughed, yet none heard threats. Mara noted ink smears on the watchchain, matching blue stains from the defendant's desk blotter. The Councilman wore polished grief, offering condolences while avoiding every question about travel permits. Mara inhaled, then lifted the glove carefully, finding a hotel keycard stamped with her own name. The coroner whispered poison, but Mara saw no needle marks, only a thin ring of chalk dust. From the gallery, a violinist fled, knocking over seating, and swore the murderer wore a white scarf.
created_at
"2026-03-18T11:17:13.702Z"
3/18/2026, 11:17:13 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
454
moderation_latency
(null)
generation_time
1335
tokens_prompt
46
tokens_completion
245
native_tokens_prompt
41
native_tokens_completion
206
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
0.0002657
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0cbede442ac052da0169ba89b9c1c88195b0eeec292df812fa"
is_byok
false
latency
192
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-1773832633-0QIuO0VEoTcDHQmjYUyG"
upstream_id
"resp_0cbede442ac052da0169ba89b9c1c88195b0eeec292df812fa"
total_cost
0.0002657
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
3.38%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
18
1
18
2
17
3
14
4
15
5
14
6
16
7
17
8
17