NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09Z18MPSZWYH1N430HPTRT
Run Details
Model:
GPT-5.4 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.9s
Cost:
$0.000237
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
3.67%
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
Detective Mara Kline arrived at Blackwell Manor, following rumors of stolen jewels and a sudden, silent death inside. The butler led her through corridors scented with lavender, where rain tapped stained glass like cautious fingertips. At the ballroom doors, Inspector Hargrove waited, insisting the victim fell alone, yet no footprints appeared. Lieutenant Sato measured the body beside an overturned violin, its strings gleaming oddly, unbroken despite chaos. Dr. Weller reported a puncture wound and poisoned blood, though the air smelled of clean, lemon polish. Mara studied the fireplace ash, finding a ring of soot too neat, as if arranged deliberately. Guests gathered behind velvet curtains, trading whispers, each denying access to the study during midnight. From the locked desk, Mara uncovered a torn invitation, addressed to no one, and signed with initials only.
created_at
"2026-03-18T11:05:47.55Z"
3/18/2026, 11:05:47 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1069
moderation_latency
(null)
generation_time
1802
tokens_prompt
46
tokens_completion
228
native_tokens_prompt
41
native_tokens_completion
183
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
0.00023695
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_07008306cfb5c1430169ba870b99cc8197b2c87f299dad9dee"
is_byok
false
latency
173
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-1773831947-kOQEbaRQgqlkzWiVn4bQ"
upstream_id
"resp_07008306cfb5c1430169ba870b99cc8197b2c87f299dad9dee"
total_cost
0.00023695
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
3.67%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
18
1
17
2
16
3
16
4
17
5
16
6
15
7
18