NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09BS4M8MGTCFR77V3DTQNV
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1.4s
Cost:
$0.000850
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
83.14%
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 manor windows shut, while guests whispered over silverware and secrets, unaware that someone had already arranged death. Inspector Vale arrived late, carrying a damp coat, a notebook, and the tired expression of someone expecting lies tonight. In the ballroom, Lady Merrow lay beside the piano, her pearl necklace snapped, her hand still clutching a burned match. No one screamed immediately; first came silence, then the careful shifting of suspects, each remembering something inconvenient about the victim. Vale knelt, studying the carpet, where muddy prints led nowhere and a faint scent of lavender masked something sharper. The butler insisted the doors stayed locked, though his trembling fingers suggested he had unlocked them for someone after midnight. Above the storm, a clock struck once, and every guest turned toward the sound, as if hearing a verdict.
created_at
"2026-03-18T10:55:16.641Z"
3/18/2026, 10:55:16 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
385
moderation_latency
(null)
generation_time
1265
tokens_prompt
46
tokens_completion
229
native_tokens_prompt
41
native_tokens_completion
182
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
0.00084975
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0c005d9f725fbb330169ba8494b18881969cea02ba1655e2ab"
is_byok
false
latency
167
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-1773831316-UDFHCz2DMX8FmlIktTyt"
upstream_id
"resp_0c005d9f725fbb330169ba8494b18881969cea02ba1655e2ab"
total_cost
0.00084975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
83.14%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
19
2
20
3
20
4
19
5
20
6
19