NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1H18C0WVV4SQ3HR2G8GQ0Q
Run Details
Model:
GPT-5.4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.2s
Cost:
$0.001992
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 rattled Blackwood Manor as guests gathered silently, unaware the night would end with one among them dead before dawn. At precisely eight, the chandelier flickered twice, and Lady Harrow smiled thinly, concealing dread beneath her diamonds and velvet. No one noticed the butler's trembling hands, nor the muddy footprints drying beside the library door's tarnished brass threshold. During supper, conversation sparkled politely, yet every laugh sounded strained, as though rehearsed for an audience of judges. Then the clock struck nine, and somewhere deep inside the house, a woman screamed once before silence swallowed everything.
created_at
"2026-03-06T12:12:52.998Z"
3/6/2026, 12:12:52 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
465
moderation_latency
(null)
generation_time
4182
tokens_prompt
46
tokens_completion
163
native_tokens_prompt
41
native_tokens_completion
126
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
0.0019925
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_05d495d1280f7e940169aac4c50fd081968c5c014a2738c46f"
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-1772799173-uxzf5XyIePOAhlA9y4PB"
upstream_id
"resp_05d495d1280f7e940169aac4c50fd081968c5c014a2738c46f"
total_cost
0.0019925
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