NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07FW0T275T06DY8900RT9B
Run Details
Model:
GPT-5.4 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.4s
Cost:
$0.000256
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.26%
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 old mansion loomed over foggy cliffs as Detective Mara Voss arrived, summoned by frantic coastal townsfolk. Inside, servants whispered of sudden thunder, and every clock chimed wrong, marking minutes that refused to align. At the foyer, a body lay near the marble stairs, dressed neatly, yet eyes staring elsewhere. The victim, Sir Alton Mercer, held a shattered pocketwatch, its hands frozen between betrayal and prayer. Mara knelt beside him, noting salt stains, vanished candles, and a crimson ribbon pinned to linen. Constable Price insisted the lock was sealed, though seawind scratched windows from the stormy north. A maid named Elsie begged silence, swearing she heard violin music behind locked study doors. From that study, smoke curled upward, though no flame burned, and the air smelled metallic. Mara asked everyone to recount their hours, while the tide tapped rhythms against the stained glass.
created_at
"2026-03-18T10:22:33.514Z"
3/18/2026, 10:22:33 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
490
moderation_latency
(null)
generation_time
1260
tokens_prompt
46
tokens_completion
239
native_tokens_prompt
41
native_tokens_completion
198
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
0.0002557
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0181e77130c288d10169ba7ce996f08196ba320557136e226b"
is_byok
false
latency
214
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-1773829353-IsBvZBxuPMBiZDoBluxH"
upstream_id
"resp_0181e77130c288d10169ba7ce996f08196ba320557136e226b"
total_cost
0.0002557
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
0.26%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
17
1
17
2
16
3
16
4
16
5
15
6
15
7
15
8
16