NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A13QXWV5V34WJT6DFTVBN
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.8s
Cost:
$0.001074
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 slicked the manor steps as Inspector Hale arrived, breathing cold air, and noticed a locked study door tonight again. Inside, Dr. Morland lay across the library rug, eyes open, a silver letter opener planted beside his hand quietly there. Servants whispered that the doctor argued earlier with Sir Malcolm over debts and a missing sapphire heirloom from the vault. Hale lifted the opener, finding no blood on its edge, yet powdery ash coated the blade almost everywhere today too. The grandfather clock stopped at 9:17, while windows stayed bolted, leaving no sound except thunder for hours afterward outside alone. Sir Malcolm stood pale, claiming innocence, and demanded Hale examine his alibi over brandy and candles right away in silence. When Hale questioned the butler, he noticed a trail of soot leading from hearth to study near midnight carefully wiped.
created_at
"2026-03-18T11:06:55.623Z"
3/18/2026, 11:06:55 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4504
moderation_latency
(null)
generation_time
4701
tokens_prompt
46
tokens_completion
225
native_tokens_prompt
41
native_tokens_completion
853
native_tokens_completion_images
0
native_tokens_reasoning
668
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
0.00107445
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_007b74f62e33d8c10169ba874fae448196ac75f05ad64fb8bb"
is_byok
false
latency
269
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-1773832015-ZqRsI0KUSqGBFwWfeyJf"
upstream_id
"resp_007b74f62e33d8c10169ba874fae448196ac75f05ad64fb8bb"
total_cost
0.00107445
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20