NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GJ8DTSAQWBWPG97VR6D43
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.3s
Cost:
$0.001888
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
40.25%
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 combed the windows of Blackthorn Hall as guests gathered below, unaware that midnight would crown one among them dead. At the head of the table, Lady Vale smiled thinly, while silver flickered beside crystal and secrets breathed. No one noticed the missing portrait, nor the muddy footprints fading upstairs, nor the clock stopping three minutes early. When the butler announced supper, thunder answered first, and every candle guttered low, as though the house inhaled. Then a scream split the corridor above, sharp enough to still every hand, and dinner began with murder.
created_at
"2026-03-06T12:04:41.538Z"
3/6/2026, 12:04:41 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
404
moderation_latency
(null)
generation_time
4194
tokens_prompt
46
tokens_completion
148
native_tokens_prompt
41
native_tokens_completion
119
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
0.0018875
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0d09ff1b74fdf3d30169aac2d99a408194b2a1631253299d16"
is_byok
false
latency
144
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-1772798681-v9pEAznIB9au8KosDt5O"
upstream_id
"resp_0d09ff1b74fdf3d30169aac2d99a408194b2a1631253299d16"
total_cost
0.0018875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
40.25%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
18
2
19
3
18
4
18