NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HWXY2Z1M385V0B630HPMW
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.6s
Cost:
$0.002352
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
73.77%
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 hammered Blackthorn Manor as guests arrived in silence, each carrying secrets heavier than their dripping coats and polished shoes. At precisely eight, the chandelier flickered twice, and Lady Wren announced dinner with a smile sharpened by old grievances. No one noticed the study door ease open upstairs, nor the thin ribbon of cigar smoke curling into darkness. By dessert, thunder shook the windows, a scream split conversation apart, and every candle flame bowed toward sudden terror. They found Lord Ashcombe sprawled beside his desk, crimson soaking the Persian rug, one gloved hand clutching a silver chess knight. Inspector Vale arrived before midnight, surveyed the horrified faces, and murmured that storms made excellent accomplices for carefully planned murders.
created_at
"2026-03-06T12:27:59.817Z"
3/6/2026, 12:27:59 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
444
moderation_latency
(null)
generation_time
5538
tokens_prompt
46
tokens_completion
204
native_tokens_prompt
41
native_tokens_completion
150
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
0.0023525
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0bca6a0f3a675fde0169aac84fdf0c8197a6d62f2ebd091244"
is_byok
false
latency
159
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-1772800079-DcIlafZqDSSnRJGfwPbR"
upstream_id
"resp_0bca6a0f3a675fde0169aac84fdf0c8197a6d62f2ebd091244"
total_cost
0.0023525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
73.77%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
19
2
19
3
19
4
21
5
20