NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QCMV4KMS04AVV052PCWW5
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
19.2s
Cost:
$0.016647
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 worried the windows of Blackthorn Manor as Inspector Vale arrived, collar raised, summoned by a whisper and midnight telegram. The butler opened the door without surprise, as though death kept appointments here, and tonight had merely arrived punctually again. In the library beneath a portrait with knife bright eyes, Lord Ashcombe lay dead beside an untouched glass of brandy. His daughter stood nearest, gloved and trembling, while the family physician studied the rug as if reading confession in silence. On the mantel, seven clocks ticked different verdicts, and Vale knew someone in this house had rehearsed innocence for years. Then the widow smiled at nothing, and the inspector understood the storm outside was not the night's darkest witness here.
created_at
"2026-03-09T16:37:53.134Z"
3/9/2026, 4:37:53 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17785
moderation_latency
(null)
generation_time
19047
tokens_prompt
46
tokens_completion
197
native_tokens_prompt
41
native_tokens_completion
1103
native_tokens_completion_images
0
native_tokens_reasoning
947
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
0.0166475
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0e83de4ce38ac8f60169aef7614374819581791c5023743649"
is_byok
false
latency
264
model_permaslug
"openai/gpt-5.4-20260305"
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-1773074273-e5NaGLOvSNyJrBmf4N4r"
upstream_id
"resp_0e83de4ce38ac8f60169aef7614374819581791c5023743649"
total_cost
0.0166475
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
6
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20