NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08Y5SF08S374E1WWTCAAC6
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
7.7s
Cost:
$0.004382
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 stitched the mansion windows as Elias Vale climbed the marble steps, clutching the invitation that smelled faintly of smoke. Inside, candles trembled above a dining table set for twelve, though only eleven guests had answered Lady Merrow's summons tonight. A silver bell rang once, and every conversation died when the butler revealed the host had vanished before supper began. Then Eleanor noticed blood on the hearth, a dark thread leading from the fireplace toward the locked library door nearby. When the lights failed, someone screamed, and Elias realized the killer was already among them, breathing softly in darkness there.
created_at
"2026-03-18T10:47:50.842Z"
3/18/2026, 10:47:50 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7443
moderation_latency
(null)
generation_time
7617
tokens_prompt
46
tokens_completion
457
native_tokens_prompt
41
native_tokens_completion
967
native_tokens_completion_images
0
native_tokens_reasoning
842
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
0.00438225
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_00aeedae940db6f30169ba82d6e4948190b55f9cb1c3f09466"
is_byok
false
latency
192
model_permaslug
"openai/gpt-5.4-mini-20260317"
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-1773830870-siHOMcJe9ZW9D4tOYjkI"
upstream_id
"resp_00aeedae940db6f30169ba82d6e4948190b55f9cb1c3f09466"
total_cost
0.00438225
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
5
wordCounts
0
20
1
20
2
20
3
20
4
20