NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKAC245F86H7RWJ6CXATBVH5
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
13.2s
Cost:
$0.013452
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 battered Blackthorn Hall as Inspector Vale arrived, boots sinking into gravel, summoned before dawn by a trembling, incoherent servant. Inside, every clock had stopped at 3:17, and the candlelit foyer smelled of lilacs, gunpowder, and something metallic lingering nearby. Lady Ormond lay beneath the grand staircase, pearls scattered like teeth, one white hand closed around a bloodstained chess knight. Her husband watched from the landing, expressionless in his dressing gown, while three dinner guests stood below, shivering silently together. No window was broken, no silver missing, yet muddy footprints crossed the marble and ended abruptly before the library doors. Vale removed his gloves, surveyed the household, and understood at once that everyone present was rehearsing the same lie already.
created_at
"2026-03-09T22:39:08.473Z"
3/9/2026, 10:39:08 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11948
moderation_latency
(null)
generation_time
13063
tokens_prompt
46
tokens_completion
371
native_tokens_prompt
41
native_tokens_completion
890
native_tokens_completion_images
0
native_tokens_reasoning
722
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
0.0134525
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0695871f40c67bfa0169af4c0c8c4c8197a40b9b280ebedcfe"
is_byok
false
latency
178
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-1773095948-5obhBiikYwfiLqEOtW3y"
upstream_id
"resp_0695871f40c67bfa0169af4c0c8c4c8197a40b9b280ebedcfe"
total_cost
0.0134525
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