NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07DJPFB6KMAQ45JV0WA78G
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.5s
Cost:
$0.000877
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
76.41%
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 polished the manor windows as Detective Vale arrived, summoned by a trembling housekeeper who refused to meet his eyes. Inside, the guests clustered beneath chandeliers, their laughter brittle, their champagne untouched, while somewhere above them, a door slammed. Vale found the body in the library, sprawled beside a toppled lamp, one hand clutching a letter stained with wax. The victim, Sir Alistair Morrow, still wore his dinner jacket, though his throat bore a thin, precise line of crimson. No one had entered the room since midnight, said the butler, yet mud tracked across the carpet told another story. Vale knelt beside the hearth, noting the missing portrait, the broken clock, and the scent of jasmine lingering faintly. Then he noticed the letter addressed to his own name, and everyone in the room suddenly stopped breathing.
created_at
"2026-03-18T10:21:18.426Z"
3/18/2026, 10:21:18 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
401
moderation_latency
(null)
generation_time
1346
tokens_prompt
46
tokens_completion
219
native_tokens_prompt
41
native_tokens_completion
188
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
0.00087675
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0a088036c03d1f9a0169ba7c9e7e9c81938788ef68afe3ecfe"
is_byok
false
latency
190
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-1773829278-3XEiTxVRShdlUPkWJVex"
upstream_id
"resp_0a088036c03d1f9a0169ba7c9e7e9c81938788ef68afe3ecfe"
total_cost
0.00087675
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
76.41%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
19
2
20
3
20
4
20
5
19
6
18