NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1JD8T7B1BWRR2VGQRFMBNX
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
4.4s
Cost:
$0.002037
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
84.45%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain hammered Blackthorn Hall as mourners gathered beneath cracked gargoyles. Lady Wren arrived last, wearing pearls and an unreadable smile. Inside, candles trembled around portraits with eyes too knowing. The clock struck nine, and every servant flinched simultaneously. A scream split dinner's hush from somewhere beyond the library. When they entered, Lord Ashcombe lay dead beside chessmen. One white king rested in his open palm, bloodied. No window stood open, yet autumn leaves covered carpets. Detective Vale removed his gloves and studied each shocked face. Then thunder answered softly, as though the house approved.
created_at
"2026-03-06T12:36:55.247Z"
3/6/2026, 12:36:55 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
384
moderation_latency
(null)
generation_time
4361
tokens_prompt
46
tokens_completion
164
native_tokens_prompt
41
native_tokens_completion
129
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
0.0020375
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0bd47393f8c49aa40169aaca6750108197a998de1f91a7a9e6"
is_byok
false
latency
162
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-1772800615-w9k6WIk2gCvbaqziaCbd"
upstream_id
"resp_0bd47393f8c49aa40169aaca6750108197a998de1f91a7a9e6"
total_cost
0.0020375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
84.45%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
9
3
9
4
10
5
9
6
9
7
9
8
10
9
9