NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1H3KB7HF08TRJJMQ0F40R6
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.4s
Cost:
$0.001917
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
59.10%
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 needled the manor windows while twelve guests watched the chandelier tremble above the long table set for mourning tonight. Lady Vale raised her crystal glass, smiling faintly, as thunder rolled outside and silver candles guttered toward unexpected darkness. When the lights failed completely, someone inhaled sharply, a chair scraped once, and a single shot shattered everything inside. Silence returned first, then screaming, as electricity flickered back and revealed Lady Vale collapsed over the untouched dessert. On the white linen beneath her hand, someone had written one word in wine: forgiven, though nobody looked relieved.
created_at
"2026-03-06T12:14:09.773Z"
3/6/2026, 12:14:09 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1703
moderation_latency
(null)
generation_time
5187
tokens_prompt
46
tokens_completion
163
native_tokens_prompt
41
native_tokens_completion
121
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
0.0019175
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_06b442a8180e22190169aac511d4608196a380b21c5b960b44"
is_byok
false
latency
134
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-1772799249-3cyD1D18xYiYXBXSFm7R"
upstream_id
"resp_06b442a8180e22190169aac511d4608196a380b21c5b960b44"
total_cost
0.0019175
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
59.10%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
19
2
19
3
18
4
19